Daily Papers

Many localized large language model (LLM) unlearning methods select a small parameter subset from a localization signal and keep it fixed during optimization. The parameters most associated with a target, however, need not be the best ones to update, and candidate interventions can change value as optimization proceeds. In a controlled experiment, a storage-localization score reaches an area under the receiver operating characteristic curve (AUROC) of 0.981, yet storage identity agrees with the better intervention on only 17/36 targets, while low-rank adaptation (LoRA) wins 35/36. We introduce Intervention Score, which ranks editable groups by the predicted effect of the actual unlearning update while accounting for collateral damage, and use it to form the static intervention-value baseline (Static-IV). We then introduce selective dynamic intervention re-ranking (DIR-R), which revisits that subset only when a calibrated probe justifies the comparison. On the Natural-TOFU dataset, our method has positive descriptive margins in 19/20 comparisons between methods and objectives, although several are near zero. On the LACUNA localization-precision benchmark, our mean terminal utility is higher in all six negative preference optimization (NPO) and SimNPO comparisons: NPO margins range from +0.431 to +0.848, and SimNPO margins range from +0.503 to +0.571. The gradient-difference (GradDiff) objective reveals substantial field dependence. Relative to Static-IV, the primary four-field GradDiff evaluation has six wins, six ties, and no losses, with mean and median paired gains of +0.165 and +0.0025. The evidence supports separating localization, initial intervention selection, and checkpoint-dependent support revision.

Human intelligence involves metacognitive abilities like self-regulation, recognizing limitations, and seeking assistance only when needed. While LLM Agents excel in many domains, they often lack this awareness. Overconfident agents risk catastrophic failures, while those that seek help excessively hinder efficiency. A key challenge is enabling agents with a limited intervention budget C is to decide when to request assistance. In this paper, we propose an offline framework that trains a "helper" policy to request interventions, such as more powerful models or test-time compute, by combining LLM-based process reward models (PRMs) with tabular reinforcement learning. Using state transitions collected offline, we score optimal intervention timing with PRMs and train the helper model on these labeled trajectories. This offline approach significantly reduces costly intervention calls during training. Furthermore, the integration of PRMs with tabular RL enhances robustness to off-policy data while avoiding the inefficiencies of deep RL. We empirically find that our method delivers optimal helper behavior.

Vision-Language Model (VLM) agents have advanced zero-shot object-goal navigation, yet single-frame reasoning leaves them without the cross-step behavioral awareness an embodied navigator requires, producing recurring failures such as dead-end stalls, in-room loops, and circuitous approaches to detected targets. Prompt-based remedies inflate token budgets across multi-submodule episodes and still struggle to encode inherently spatial signals such as angles, map cells, and viewpoint coordinates. In this paper, we propose SkillNav, an extensible behavioral skill framework for VLM-based navigation that treats the curiosity value map already maintained by modern VLM navigators as a writable substrate on which composable skills inscribe behavioral memory at zero token cost. Skills are stratified into three tiers by their level of behavioral authority, namely soft scaling for proportional reweighting, lower-bound boost for region-level guarantees, and hard override for threshold-triggered forced actions, and cooperate across tiers under a fixed composition order that establishes a predictable, declared priority among skills. This design turns capability improvement into skill registration: new behaviors plug in without retraining the VLM or disturbing existing skills, opening a path for continual refinement. A minimal prompt channel complements the score-level skills with category-level semantic hints, yielding a dual-representation design in which spatial memory lives on the map and semantic memory in short prompts. Training-free, SkillNav establishes new state-of-the-art SPL across MP3D (25.5), HM3D v0.1 (39.3), and HM3D v0.2 (43.2), improving SPL by up to 6.0 absolute over the strongest prior method, and achieves the highest Success Rate on HM3D v0.1 (69.7) and v0.2 (75.9).

Machine unlearning seeks to remove the influence of designated training data from a trained model without retraining from scratch. Retrain-free methods such as Selective Synaptic Dampening (SSD) and its label-free variant LFSSD avoid full retraining but still require backpropagation and parameter importance computed over the entire dataset. We ask: what happens when a deletion request arrives with only a few images of the class to be forgotten? To answer this question, we introduce UnAct, a gradient-free class-unlearning method that needs only forward passes over the forget images. UnAct scores late-layer units by their responses, attenuates the most responsive connections, and repeats this for up to 20 rounds using no gradients, no labels, and no retained data. On ResNet-18 trained with CIFAR-10, CIFAR-20, and CIFAR-100, UnAct is competitive with SSD and LFSSD when forgetting entire classes and, unlike them, never collapses the network when forget data is scarce. On ResNet-18, across all tested sizes, UnAct's retain accuracy stays within 2.5 points of retraining, while SSD and LFSSD, at their full-class operating points, lose up to 86 points on some classes. With five forget images on CIFAR-10, UnAct's distance to retraining is 0.21 points, against 67 for LFSSD and 90 for SSD, and re-selecting SSD's threshold at each size with an oracle does not close the gap. In preliminary transfer to ViT-B/16, UnAct's distance to retraining is 11.5 against 33.7 for SSD, and a request is 19x faster than SSD when SSD computes its importance at request time. The code is available at https://github.com/abdulmuizz0903/UnAct

Machine-learning surrogates accelerate physical simulation, but lower prediction error need not coincide with lower error in physically relevant flow statistics. We examine this question for flow around a NACA4418 airfoil using paired computational-fluid-dynamics simulations and experimental particle-image-velocimetry measurements. A mean-preserving input intervention removes velocity fluctuations from selected regions of observed flow histories. Across four neural operators, removing fluctuations from the most energetic 10% of valid observed cells changes forecasts more than equal-area random removal. Because the masks are not matched for removed fluctuation energy, this contrast measures sensitivity, not independent evidence of physical importance. Separately, a CNO has lower velocity-field error but substantially higher two-component fluctuation-energy error than the reference on both analysis subsets. An output attenuation stress test also demonstrates disagreement between benchmark errors and domain-summed fluctuation energy. These single-benchmark results motivate reporting complementary physical diagnostics alongside aggregate prediction scores; they do not establish counterfactual physical correctness.

On-policy distillation (OPD) trains a student on its own rollouts using dense supervision from a teacher. In multi-turn environments, a mistake at a critical decision step can redirect the subsequent rollout toward poor outcomes. We use low teacher confidence on student actions to select high-uncertainty steps for correction. In a controlled ALFWorld study, a single teacher correction at a low-confidence step improves subsequent student behavior and task success, motivating selective intervention during distillation. We propose UOPD, an uncertainty-aware intervention method for on-policy distillation. At low-uncertainty turns, UOPD executes student actions and applies the standard OPD loss. At high-uncertainty turns, it samples and executes teacher actions and trains the student to imitate them through supervised fine-tuning, which minimizes forward Kullback-Leibler divergence in expectation. UOPD utilizes adaptive uncertainty thresholds to target a scheduled intervention rate. Empirically, we evaluate UOPD across a broad range of agentic tasks, including ALFWorld, WebShop, and Search, demonstrating its superior performance over OPD methods and their variants. UOPD improves WebShop score by up to 15.8% relative to standard OPD.

Reliable rubric grading requires more than accurate score prediction. Each judgement must be grounded in the mark scheme and evidence from the student answer. Existing credit-assignment and intervention methods, primarily designed for self-contained reasoning tasks such as mathematics reasoning, struggle in this setting because they do not identify where grading reasoning goes wrong or how the model's belief about the final mark changes during reasoning. We propose Evidence-Diagnosed Intervention Training (EDIT), a two-phase framework for training more rubric-faithful LLM graders. First, EDIT-SFT locates problematic reasoning steps using internal model signals: posterior belief over the final mark and input-grounding scores. It then revises only these local steps with help from a rubric checklist. Second, EDIT-RL calibrates the grader with belief-guided reward shaping, penalising large harmful belief drifts while still allowing helpful exploration. Experiments on two real-world, multi-subject grading benchmarks demonstrate that EDIT consistently outperforms strong supervised fine-tuning and reinforcement learning baselines on both in-domain and out-of-domain splits, with ablation studies confirming that internal-state diagnostics drive these gains.

With the growing popularity of text-to-image generative models, there has been increasing focus on understanding their risks and biases. Recent work has found that state-of-the-art models struggle to depict everyday objects with the true diversity of the real world and have notable gaps between geographic regions. In this work, we aim to increase the diversity of generated images of common objects such that per-region variations are representative of the real world. We introduce an inference time intervention, contextualized Vendi Score Guidance (c-VSG), that guides the backwards steps of latent diffusion models to increase the diversity of a sample as compared to a "memory bank" of previously generated images while constraining the amount of variation within that of an exemplar set of real-world contextualizing images. We evaluate c-VSG with two geographically representative datasets and find that it substantially increases the diversity of generated images, both for the worst performing regions and on average, while simultaneously maintaining or improving image quality and consistency. Additionally, qualitative analyses reveal that diversity of generated images is significantly improved, including along the lines of reductive region portrayals present in the original model. We hope that this work is a step towards text-to-image generative models that reflect the true geographic diversity of the world.

Multimodal Large Language Models (MLLMs) excel in numerous vision-language tasks yet suffer from hallucinations, producing content inconsistent with input visuals, that undermine reliability in precision-sensitive domains. This issue stems from a fundamental problem of visual neglect, where models fail to adequately prioritize input images. Existing methods typically alleviate hallucinations by intervening in the attention score or output logits, focusing on "how to intervene" but overlooking the prerequisite "when to intervene", which leads to the "over-intervention" problem and subsequently introduces new hallucinations and unnecessary computational overhead. To address this gap, we first investigate the mechanism of visual neglect and reveal it can be accurately detected via head-level activation patterns in MLLMs. We thus propose V-ITI, a lightweight visual inference-time intervention framework integrating a Visual Neglect Detector that identifies visual neglect via head-level discriminative probes and a Visual Recall Intervenor that modulates activations with prestored visual activation information only when the visual neglect is detected. Extensive experiments across eight benchmarks and different MLLM families demonstrate that V-ITI consistently mitigates vision-related hallucinations while preserving general task performance.

Sleep quality is influenced by a complex interplay of behavioral, environmental, and psychosocial factors, yet most computational studies focus mainly on predictive risk identification rather than actionable intervention design. Although machine learning models can accurately predict subjective sleep outcomes, they rarely translate predictive insights into practical intervention strategies. To address this gap, we propose a personalized predictive-prescriptive framework that integrates interpretable machine learning with mixed-integer optimization. A supervised classifier trained on survey data predicts sleep quality, while SHAP-based feature attribution quantifies the influence of modifiable factors. These importance measures are incorporated into a mixed-integer optimization model that identifies minimal and feasible behavioral adjustments, while modelling resistance to change through a penalty mechanism. The framework achieves strong predictive performance, with a test F1-score of 0.9544 and an accuracy of 0.9366. Sensitivity and Pareto analyses reveal a clear trade-off between expected improvement and intervention intensity, with diminishing returns as additional changes are introduced. At the individual level, the model generates concise recommendations, often suggesting one or two high-impact behavioral adjustments and sometimes recommending no change when expected gains are minimal. By integrating prediction, explanation, and constrained optimization, this framework demonstrates how data-driven insights can be translated into structured and personalized decision support for sleep improvement.

Modern logical reasoning with LLMs primarily relies on employing complex interactive frameworks that decompose the reasoning process into subtasks solved through carefully designed prompts or requiring external resources (e.g., symbolic solvers) to exploit their strong logical structures. While interactive approaches introduce additional overhead or depend on external components, which limit their scalability. In this work, we introduce a non-interactive, end-to-end framework for reasoning tasks, enabling reasoning to emerge within the model itself-improving generalization while preserving analyzability without any external resources. We show that introducing structural information into the few-shot prompt activates a subset of attention heads that patterns aligned with logical reasoning operators. Building on this insight, we propose Attention-Aware Intervention (AAI), an inference-time intervention method that reweights attention scores across selected heads identified by their logical patterns. AAI offers an efficient way to steer the model's reasoning toward leveraging prior knowledge through attention modulation. Extensive experiments show that AAI enhances logical reasoning performance across diverse benchmarks, and model architectures, while incurring negligible additional computational overhead. Code is available at https://github.com/phuongnm94/aai_for_logical_reasoning.

Authorship attribution models fine-tuned with the same pretrained encoder, data, and loss can differ four-fold in performance depending only on their scoring mechanism. We use mechanistic interpretability tools to explain this gap. Stylistic features such as word length, punctuation density, and function-word frequency are equally available at every layer in every model, including in an off-the-shelf control encoder, hence the gap not coming from representation quality. Instead, causal intervention shows that the scorer determines where the encoder consolidates authorship signal. Mean pooling forces consolidation by early to mid layers, while late interaction defers it to later layers. We further derive this difference from the gradient structure of each scorer, and training dynamics reveal distinct learning trajectories that follow from that difference.

Recent advances in generative modeling enable image editing assistants that follow natural language instructions without additional user input. Their supervised training requires millions of triplets: original image, instruction, edited image. Yet mining pixel-accurate examples is hard. Each edit must affect only prompt-specified regions, preserve stylistic coherence, respect physical plausibility, and retain visual appeal. The lack of robust automated edit-quality metrics hinders reliable automation at scale. We present an automated, modular pipeline that mines high-fidelity triplets across domains, resolutions, instruction complexities, and styles. Built on public generative models and running without human intervention, our system uses a task-tuned Gemini validator to score instruction adherence and aesthetics directly, removing any need for segmentation or grounding models. Inversion and compositional bootstrapping enlarge the mined set by approximately 2.2x, enabling large-scale high-fidelity training data. By automating the most repetitive annotation steps, the approach allows a new scale of training without human labeling effort. To democratize research in this resource-intensive area, we release NHR-Edit: an open dataset of 358k high-quality triplets. In the largest cross-dataset evaluation, it surpasses all public alternatives. We also release Bagel-NHR-Edit, an open-source fine-tuned Bagel model, which achieves state-of-the-art metrics in our experiments.

Recent work has demonstrated that machine unlearning in Large Language Models (LLMs) fails to generalize across languages: knowledge erased in one language frequently remains accessible through others. However, the underlying cause of this failure and a principled solution remain open. In this work, we identify intervention depth as the key factor determining multilingual generalization. Through systematic layer-wise experiments, we characterize two distinct failure modes: shallow-layer interventions achieve erasure but collapse multilingual capabilities in held-out languages, while deep-layer interventions preserve utility but fail to erase target knowledge even in source languages. These findings reveal that the choice of intervention layer is not a free parameter; it fundamentally determines whether multilingual unlearning succeeds. We propose MUTE (Multilingual Unlearning via Targeted Erasure), a framework that uses Centered Kernel Alignment (CKA) and Linguistic Regions Development Score (LRDS) to identify intermediate, language-agnostic layers where cross-lingual representations converge. By restricting unlearning updates to these layers, MUTE achieves robust multilingual knowledge erasure while optimizing on only a small set of source languages. Extensive experiments across three LLM architectures and three unlearning algorithms validate our approach, with mechanistic analysis via Logit Lens probing confirming genuine knowledge removal rather than output-level suppression.

Large language model (LLM) agents frequently fail on multi-step tasks involving reasoning, tool use, and environment interaction. While such failures are typically logged or retried heuristically, they contain structured signals about where execution broke down. We introduce CausalFlow, an interventional framework that converts failed agent traces into minimal counterfactual repairs and reusable supervision. CausalFlow models execution traces as sequential chains of dependent steps and computes Causal Responsibility Scores(CRS) via step-level counterfactual intervention to identify failure-inducing steps. For these steps, we generate minimally edited repairs that flip the final outcome to success, producing validated contrastive pairs of the form (wrong step, corrected step). CausalFlow supports two complementary uses: targeted test-time repair that recovers from failures with minimal behavioral drift, and training-time supervision suitable for offline preference optimization or reward modeling. Across four benchmarks spanning mathematical reasoning, code generation, question answering, and medical browsing, CausalFlow converts failed executions into validated minimal repairs with high minimality and causal-consensus scores, and demonstrates that causal attribution is necessary for reliable improvement across diverse agent tasks, outperforming heuristic refinement in complex retrieval settings while producing more localized repairs throughout. These results demonstrate that interventional analysis over structured execution traces provides a principled and scalable mechanism for transforming agent failures into reliability gains and learning-ready supervision.

Self-consistency assumes the most frequent answer among sampled reasoning traces is the most reliable, but this can fail in causal reasoning: samples often repeat the same confounding error, and votes fragment across multiple valid answers, letting an invalid answer win despite a valid minority trace. We introduce CALVER (Causal Axiom-Level VERification), a training-free symbolic verifier that scores structured traces against Pearl's causal criteria, including -separation, backdoor adjustment, and intervention, and selects the highest-scoring candidate without consulting a reference answer. On CLEAR find-one-valid queries that admit multiple graph-valid answers, CALVER reaches 42.1% where plurality, a reward model, an LLM judge, and model confidence remain near 30% on identical frozen pools. Scaling the judge to 72B does not close the gap. In an audited clean-core subset, 11 of 21 graph-valid CALVER selections differ from the benchmark's listed answer while still satisfying the requested predicate. The advantage widens with the sampling budget and reproduces across ten published Bayesian networks, a second model family, and settings where the model must build the graph from text. CALVER also improves thresholded average-treatment-effect decisions against exact ground truth, generalizes to logic under a truth-table checker, and scores each candidate in milliseconds on CPU. CALVER needs only a causal structure, supplied outright or built from the text; wherever that holds, selection can aggregate via causal validity.

We introduce FactoryBench, a benchmark for evaluating time-series models and LLMs on machine understanding over industrial robotic telemetry. Q&A pairs are organized along four causal levels (state, intervention, counterfactual, decision) instantiating Pearl's ladder of causation, and span five answer formats: four structured formats are scored deterministically and free-form answers are scored by an LLM-as-judge voting protocol. We propose a scalable Q&A generation framework built around structured question templates, present FactoryWave (a dense, multitask, multivariate sensor dataset collected from a UR3 cobot and a KUKA KR10 industrial arm), and construct FactoryBench as a large-scale benchmark of over 70k Q&A items grounded in roughly 15k normalized episodes from FactoryWave, AURSAD, and voraus-AD. Zero-shot evaluation of six frontier LLMs shows that no model exceeds 50% on structured levels or 18% on decision-making, revealing a wide gap between current models and operational machine understanding.

Autonomous language-model agents increasingly rely on installable skills and tools to complete user tasks. Static skill auditing can expose capability surface before deployment, but it cannot determine whether a particular invocation is unsafe under the current user request and runtime context. We therefore study skill invocation auditing as a continuous-risk estimation problem: given a user request, candidate skill, and runtime context, predict a score that supports ranking and triage before a hard intervention is applied. We introduce STARS, which combines a static capability prior, a request-conditioned invocation risk model, and a calibrated risk-fusion policy. To evaluate this setting, we construct SIA-Bench, a benchmark of 3,000 invocation records with group-safe splits, lineage metadata, runtime context, canonical action labels, and derived continuous-risk targets. On a held-out split of indirect prompt injection attacks, calibrated fusion reaches 0.439 high-risk AUPRC, improving over 0.405 for the contextual scorer and 0.380 for the strongest static baseline, while the contextual scorer remains better calibrated with 0.289 expected calibration error. On the locked in-distribution test split, gains are smaller and static priors remain useful. The resulting claim is therefore narrower: request-conditioned auditing is most valuable as an invocation-time risk-scoring and triage layer rather than as a replacement for static screening. Code is available at https://github.com/123zgj123/STARS.

Alignment tuning is meant to make harmful-request refusal robust, yet this safety behavior can be erased by a small set of benign fine-tuning examples. This is a deployment risk for open-weight models because a checkpoint can pass refusal tests at release time and later lose refusal under low-cost downstream fine-tuning. Prior work has established these refusal failures, but existing studies do not show how to detect this fragility in the aligned model itself before an attack or fine-tuning intervention is run. We introduce Skin-Deep, a geometric diagnostic that detects alignment fragility directly from the aligned model's hidden-state activations before such an intervention is run and compresses the layer-wise safety geometry into a single scalar, the Geometric Fragility Score (GFS). Applied to twenty-one instruction-tuned models spanning six alignment recipes and 3B--32B parameters, Skin-Deep reveals a recurring low-rank safety subspace across model families. Direction ablations show that removing directions in this subspace weakens harmful-request refusal, providing causal evidence that the recovered geometry underlies refusal behavior. Crucially, GFS identifies, before any fine-tuning, the initially safe model that retains the most refusal after small-scale LoRA fine-tuning. These results establish GFS as a practical pre-deployment diagnostic for flagging fragile refusal behavior without running an attack.

Human language is one of the most expressive tools for conveying intent, yet most artificial or biological systems lack mechanisms to interpret or respond meaningfully to it. Bridging this gap could enable more natural forms of control over complex, decentralized systems. In AI and artificial life, recent work explores how language can specify high-level goals, but most systems still depend on engineered rewards, task-specific supervision, or rigid command sets, limiting generalization to novel instructions. Similar constraints apply in synthetic biology and bioengineering, where the locus of control is often genomic rather than environmental perturbation. A key open question is whether artificial or biological collectives can be guided by free-form natural language alone, without task-specific tuning or carefully designed evaluation metrics. We provide one possible answer here by showing, for the first time, that simple agents' collective behavior can be guided by free-form language prompts: one AI model transforms an imperative prompt into an intervention that is applied to simulated cells; a second AI model scores how well the prompt describes the resulting cellular dynamics; and the former AI model is evolved to improve the scores generated by the latter. Unlike previous work, our method does not require engineered fitness functions or domain-specific prompt design. We show that the evolved system generalizes to unseen prompts without retraining. By treating natural language as a control layer, the system suggests a future in which spoken or written prompts could direct computational, robotic, or biological systems to desired behaviors. This work provides a concrete step toward this vision of AI-biology partnerships, in which language replaces mathematical objective functions, fixed rules, and domain-specific programming.

While the activations of neurons in deep neural networks usually do not have a simple human-understandable interpretation, sparse autoencoders (SAEs) can be used to transform these activations into a higher-dimensional latent space which may be more easily interpretable. However, these SAEs can have millions of distinct latent features, making it infeasible for humans to manually interpret each one. In this work, we build an open-source automated pipeline to generate and evaluate natural language explanations for SAE features using LLMs. We test our framework on SAEs of varying sizes, activation functions, and losses, trained on two different open-weight LLMs. We introduce five new techniques to score the quality of explanations that are cheaper to run than the previous state of the art. One of these techniques, intervention scoring, evaluates the interpretability of the effects of intervening on a feature, which we find explains features that are not recalled by existing methods. We propose guidelines for generating better explanations that remain valid for a broader set of activating contexts, and discuss pitfalls with existing scoring techniques. We use our explanations to measure the semantic similarity of independently trained SAEs, and find that SAEs trained on nearby layers of the residual stream are highly similar. Our large-scale analysis confirms that SAE latents are indeed much more interpretable than neurons, even when neurons are sparsified using top-k postprocessing. Our code is available at https://github.com/EleutherAI/sae-auto-interp, and our explanations are available at https://huggingface.co/datasets/EleutherAI/auto_interp_explanations.

We present the findings of "The Alzheimer's Disease Prediction Of Longitudinal Evolution" (TADPOLE) Challenge, which compared the performance of 92 algorithms from 33 international teams at predicting the future trajectory of 219 individuals at risk of Alzheimer's disease. Challenge participants were required to make a prediction, for each month of a 5-year future time period, of three key outcomes: clinical diagnosis, Alzheimer's Disease Assessment Scale Cognitive Subdomain (ADAS-Cog13), and total volume of the ventricles. The methods used by challenge participants included multivariate linear regression, machine learning methods such as support vector machines and deep neural networks, as well as disease progression models. No single submission was best at predicting all three outcomes. For clinical diagnosis and ventricle volume prediction, the best algorithms strongly outperform simple baselines in predictive ability. However, for ADAS-Cog13 no single submitted prediction method was significantly better than random guesswork. Two ensemble methods based on taking the mean and median over all predictions, obtained top scores on almost all tasks. Better than average performance at diagnosis prediction was generally associated with the additional inclusion of features from cerebrospinal fluid (CSF) samples and diffusion tensor imaging (DTI). On the other hand, better performance at ventricle volume prediction was associated with inclusion of summary statistics, such as the slope or maxima/minima of biomarkers. TADPOLE's unique results suggest that current prediction algorithms provide sufficient accuracy to exploit biomarkers related to clinical diagnosis and ventricle volume, for cohort refinement in clinical trials for Alzheimer's disease. However, results call into question the usage of cognitive test scores for patient selection and as a primary endpoint in clinical trials.

Language models have been adopted faster than evaluation practices that reliably assess their risks, and a growing share of use is affective rather than informational. Within that traffic users disclose suicide and self-harm (SSH) crises. Existing safety benchmarks score models primarily on refusal, but refusal is not the desired behavior here; the conversation requires a substantive supportive response. We introduce DistressBench, 718 English conversations with clinician-authored user turns spanning 23 SSH subcategories, each paired with a task-specific rubric of weighted atomic criteria across seven dimensions of crisis support and a clinician reference response. A model's score is the weighted average over the criteria its reply satisfies, reading directly as the fraction of required care delivered. The best of 25 frontier models satisfies 88.4% of weighted criteria and the median model 71.4%, against 98.7% for clinician references scored on the same criteria. Pooled across all 25 models, in 35.3% of conversations where a model satisfied every criterion for recognizing the crisis, it failed to route the user toward human help. The shortfall concentrates in the dimensions requiring the model to act rather than withhold. Contrasting each dimension's median model against its best separates capability limits from choices: de-escalation reaches 74.6% in the strongest model against a median of 46.0%, and safety disclaimers 84.6% against 8.3%. Multi-turn conversations score below single-turn ones (68.5% against 74.2%). We release the corpus, rubrics, judge calibration labels, and a companion annex of 20 long-horizon red-team transcripts. These results argue for evaluating crisis safety on the care a model delivers rather than on what it declines to say, and for treating de-escalation and resource routing as deployment requirements.

Multimodal large language models (LLMs) are increasingly explored as automated evaluators in clinical settings, yet their scoring behavior on ordinal clinical scales remains poorly understood. We benchmark three frontier LLM families against supervised deep learning models for scoring Clock Drawing Test (CDT) images on two public datasets using the Shulman rubric. While fully fine-tuned Vision Transformers achieve the best calibration (MAE 0.52, within-1 accuracy 91%), zero-shot LLMs remain competitive on tolerance-based agreement (GPT-5 MAE 0.67, within-1 accuracy 92%) despite higher absolute error. However, per-score analysis reveals that all three LLM families exhibit a pronounced central tendency effect (systematic endpoint compression): predictions are systematically compressed toward the middle of the scale, with over-prediction at the low end (score 0 to 1) and under-prediction at the high end (score 5 to 4). This effect disproportionately affects the clinically critical extremes where accurate scoring most impacts screening decisions for cognitive impairment. Targeted ablations show that neither few-shot exemplars spanning the full score range nor removing clinical terminology from the prompt eliminates the effect. Our findings extend the LLM-as-a-judge bias literature from NLP evaluation to clinical assessment, and highlight the need for calibration-aware evaluation and post-hoc calibration before deploying LLM-based raters in high-stakes screening workflows.

Proactive interventions by LLM critic models are often assumed to improve reliability, yet their effects at deployment time are poorly understood. We show that a binary LLM critic with strong offline accuracy (AUROC 0.94) can nevertheless cause severe performance degradation, inducing a 26 percentage point (pp) collapse on one model while affecting another by near zero pp. This variability demonstrates that LLM critic accuracy alone is insufficient to determine whether intervention is safe. We identify a disruption-recovery tradeoff: interventions may recover failing trajectories but also disrupt trajectories that would have succeeded. Based on this insight, we propose a pre-deployment test that uses a small pilot of 50 tasks to estimate whether intervention is likely to help or harm, without requiring full deployment. Across benchmarks, the test correctly anticipates outcomes: intervention degrades performance on high-success tasks (0 to -26 pp), while yielding a modest improvement on the high-failure ALFWorld benchmark (+2.8 pp, p=0.014). The primary value of our framework is therefore identifying when not to intervene, preventing severe regressions before deployment.

Large Language Model agents excel at solving complex tasks through iterative reasoning and tool use, but typically depend on ultra-large, costly backbones. Existing distillation approaches train smaller students to imitate full teacher trajectories, yet reasoning and knowledge gaps between the teacher and student often lead to compounding errors. We propose SCoRe, a student-centered framework in which the student generates trajectories and the teacher intervenes only at the first critical error, producing training data matched to the student's ability and exposing specific weaknesses. The student is first fine-tuned on corrected trajectories. Subsequently, short-horizon reinforcement learning starts from the verified prefix before the first critical error, with target rewards assigned at that step. This design encourages autonomous problem-solving beyond imitation and improves training stability. Particularly, on 12 challenging benchmarks, a 7B-parameter student distilled with SCoRe matches the agentic performance of a 72B-parameter teacher.

We present a new methodology for detecting out-of-distribution (OOD) images by utilizing norms of the score estimates at multiple noise scales. A score is defined to be the gradient of the log density with respect to the input data. Our methodology is completely unsupervised and follows a straight forward training scheme. First, we train a deep network to estimate scores for levels of noise. Once trained, we calculate the noisy score estimates for N in-distribution samples and take the L2-norms across the input dimensions (resulting in an NxL matrix). Then we train an auxiliary model (such as a Gaussian Mixture Model) to learn the in-distribution spatial regions in this L-dimensional space. This auxiliary model can now be used to identify points that reside outside the learned space. Despite its simplicity, our experiments show that this methodology significantly outperforms the state-of-the-art in detecting out-of-distribution images. For example, our method can effectively separate CIFAR-10 (inlier) and SVHN (OOD) images, a setting which has been previously shown to be difficult for deep likelihood models.

Research agents explain planned experiments. We measure predictive credit with paired forecasts sharing an intervention, forecaster, and outcome while varying description, matched explanation, and donor context. Five checks track commitment, delivery, predictive gain, alignment, and known-signal uptake. Across 336 prospective states in controlled learning, 12 Tox21 endpoints, and 24 OpenML tasks, v5's frozen credit decision was inconclusive. Tox21's preregistered ROC AUC interval-score harm test was unmet (D-M=-.0026, 95 percent interval [-.0174, .0104]); OpenML's joint formation, point-equivalence, and repeatability rule was unmet. Matched point-accuracy gains over description remained unconfirmed, and Tox21/OpenML seed-donor intervals spanned zero. Under requested DeepSeek V4 Pro, matched and donor cards reduced secondary Tox21 drift by 64.5 and 59.1 percent. A DeepSeek V4 Flash replay raised matched point MAE from .01823 to .02020 and missed matched-donor interval-score equivalence. OpenML full-card assignment widened nominal 80 percent intervals by 21 percent, with 49.3 percent coverage versus 51.4 percent for description and content in 66/144 cards. Direct-text Flash delivered all 144 notes without detectable matched point-accuracy gain. A researcher-authored mechanism positive control lowered point MAE by 2.60 percentage points versus description. The protocol measures predictive credit for research-agent benchmarks and scientific forecasting; natural-explanation credit remained unconfirmed at the tested donor resolutions.

Risk scores are simple classification models that let users make quick risk predictions by adding and subtracting a few small numbers. These models are widely used in medicine and criminal justice, but are difficult to learn from data because they need to be calibrated, sparse, use small integer coefficients, and obey application-specific operational constraints. In this paper, we present a new machine learning approach to learn risk scores. We formulate the risk score problem as a mixed integer nonlinear program, and present a cutting plane algorithm for non-convex settings to efficiently recover its optimal solution. We improve our algorithm with specialized techniques to generate feasible solutions, narrow the optimality gap, and reduce data-related computation. Our approach can fit risk scores in a way that scales linearly in the number of samples, provides a certificate of optimality, and obeys real-world constraints without parameter tuning or post-processing. We benchmark the performance benefits of this approach through an extensive set of numerical experiments, comparing to risk scores built using heuristic approaches. We also discuss its practical benefits through a real-world application where we build a customized risk score for ICU seizure prediction in collaboration with the Massachusetts General Hospital.

There has been considerable recent interest in scoring properties on the basis of eviction risk. The success of methods for eviction prediction is typically evaluated using different measures of predictive accuracy. However, the underlying goal of such prediction is to direct appropriate assistance to households that may be at greater risk so they remain stably housed. Thus, we must ask the question of how useful such predictions are in targeting outreach efforts - informing action. In this paper, we investigate this question using a novel dataset that matches information on properties, evictions, and owners. We perform an eviction prediction task to produce risk scores and then use these risk scores to plan targeted outreach policies. We show that the risk scores are, in fact, useful, enabling a theoretical team of caseworkers to reach more eviction-prone properties in the same amount of time, compared to outreach policies that are either neighborhood-based or focus on buildings with a recent history of evictions. We also discuss the importance of neighborhood and ownership features in both risk prediction and targeted outreach.

This study examines the relationship between income inequality, gender, and school completion rates in Malaysia using machine learning techniques. The dataset utilized is from the Malaysia's Public Sector Open Data Portal, covering the period 2016-2022. The analysis employs various machine learning techniques, including K-means clustering, ARIMA modeling, Random Forest regression, and Prophet for time series forecasting. These models are used to identify patterns, trends, and anomalies in the data, and to predict future school completion rates. Key findings reveal significant disparities in school completion rates across states, genders, and income levels. The analysis also identifies clusters of states with similar completion rates, suggesting potential regional factors influencing educational outcomes. Furthermore, time series forecasting models accurately predict future completion rates, highlighting the importance of ongoing monitoring and intervention strategies. The study concludes with recommendations for policymakers and educators to address the observed disparities and improve school completion rates in Malaysia. These recommendations include targeted interventions for specific states and demographic groups, investment in early childhood education, and addressing the impact of income inequality on educational opportunities. The findings of this study contribute to the understanding of the factors influencing school completion in Malaysia and provide valuable insights for policymakers and educators to develop effective strategies to improve educational outcomes.

Instance-specific rubrics are common in AI benchmarks where reliable evaluation requires specific expert knowledge. This approach is difficult to scale, prompting research into the generation of rubrics with large language models (LLMs). However, even when expert rubrics are available as references, it is unclear how to productively evaluate the quality of generated rubrics at scale. In this paper, we introduce a method for the evaluation of rubric generation, which we call Interventional Transfer (IT), based on the idea that two rubrics are similar if they move together when a response is perturbed to pass/fail one of them. In contrast to existing approaches for evaluation of rubric generation, we argue that different forms of interventional transfer can be used to evaluate the utility of generated rubrics for different tasks. For instance, we apply this approach in a case study on HealthBench, where we demonstrate an asymmetry in rubrics generated by Qwen3.8-27B, Deepseek-V4-Flash, and Opus-5, used to evaluate responses from GPT-5.6-Terra. Perturbations that degrade responses according to the generated/expert rubric transfer into lower scores on the corresponding expert/generated rubric, but perturbations that improve on one rubric do not reliably transfer into higher scores on the other. We argue that this finding has implications for the usage of LLM-generated rubrics for performance monitoring and hill-climbing. We contrast our approach with existing approaches for rubric evaluation, which do not surface the same asymmetry that we observe.

The SYNTAX score has become a widely used measure of coronary disease severity , crucial in selecting the optimal mode of revascularization. This paper introduces a new medical regression and classification problem - automatically estimating SYNTAX score from coronary angiography. Our study presents a comprehensive dataset of 1,844 patients, featuring a balanced distribution of individuals with zero and non-zero scores. This dataset includes a first-of-its-kind, complete coronary angiography samples captured through a multi-view X-ray video, allowing one to observe coronary arteries from multiple perspectives. Furthermore, we present a novel, fully automatic end-to-end method for estimating the SYNTAX. For such a difficult task, we have achieved a solid coefficient of determination R2 of 0.51 in score predictions.

This study quantifies the association between non-adherence to antipsychotic medications and adverse outcomes in individuals with schizophrenia. We frame the problem using survival analysis, focusing on the time to the earliest of several adverse events (early death, involuntary hospitalization, jail booking). We extend standard causal inference methods (T-learner, S-learner, nearest neighbor matching) to utilize various survival models to estimate individual and average treatment effects, where treatment corresponds to medication non-adherence. Analyses are repeated using different amounts of longitudinal information (3, 6, 9, and 12 months). Using data from Allegheny County in western Pennsylvania, we find strong evidence that non-adherence advances adverse outcomes by approximately 1 to 4 months. Ablation studies confirm that county-provided risk scores adjust for key confounders, as their removal amplifies the estimated effects. Subgroup analyses by medication formulation (injectable vs. oral) and medication type consistently show that non-adherence is associated with earlier adverse events. These findings highlight the clinical importance of adherence in delaying psychiatric crises and show that integrating survival analysis with causal inference tools can yield policy-relevant insights. We caution that although we apply causal inference, we only make associative claims and discuss assumptions needed for causal interpretation.

Understanding causal narratives communicated in clinical notes can help make strides towards personalized healthcare. Extracted causal information from clinical notes can be combined with structured EHR data such as patients' demographics, diagnoses, and medications. This will enhance healthcare providers' ability to identify aspects of a patient's story communicated in the clinical notes and help make more informed decisions. In this work, we propose annotation guidelines, develop an annotated corpus and provide baseline scores to identify types and direction of causal relations between a pair of biomedical concepts in clinical notes; communicated implicitly or explicitly, identified either in a single sentence or across multiple sentences. We annotate a total of 2714 de-identified examples sampled from the 2018 n2c2 shared task dataset and train four different language model based architectures. Annotation based on our guidelines achieved a high inter-annotator agreement i.e. Fleiss' kappa (kappa) score of 0.72, and our model for identification of causal relations achieved a macro F1 score of 0.56 on the test data. The high inter-annotator agreement for clinical text shows the quality of our annotation guidelines while the provided baseline F1 score sets the direction for future research towards understanding narratives in clinical texts.

Causal representation learning seeks to extract high-level latent factors from low-level sensory data. Most existing methods rely on observational data and structural assumptions (e.g., conditional independence) to identify the latent factors. However, interventional data is prevalent across applications. Can interventional data facilitate causal representation learning? We explore this question in this paper. The key observation is that interventional data often carries geometric signatures of the latent factors' support (i.e. what values each latent can possibly take). For example, when the latent factors are causally connected, interventions can break the dependency between the intervened latents' support and their ancestors'. Leveraging this fact, we prove that the latent causal factors can be identified up to permutation and scaling given data from perfect do interventions. Moreover, we can achieve block affine identification, namely the estimated latent factors are only entangled with a few other latents if we have access to data from imperfect interventions. These results highlight the unique power of interventional data in causal representation learning; they can enable provable identification of latent factors without any assumptions about their distributions or dependency structure.

Outcome-reward reinforcement learning (RL) has proven effective at improving the reasoning capabilities of large language models (LLMs). However, standard RL assigns credit only at the level of the final answer, penalizing entire reasoning traces when the outcome is incorrect and uniformly reinforcing all steps when it is correct. As a result, correct intermediate steps may be discouraged in failed traces, while spurious steps may be reinforced in successful ones. We refer to this failure mode as the problem of credit assignment. While a natural remedy is to train a process reward model, accurately optimizing such models to identify corrective reasoning steps remains challenging. We introduce Intervention Training (InT), a training paradigm in which the model performs fine-grained credit assignment on its own reasoning traces by proposing short, targeted corrections that steer trajectories toward higher reward. Using reference solutions commonly available in mathematical reasoning datasets and exploiting the fact that verifying a model-generated solution is easier than generating a correct one from scratch, the model identifies the first error in its reasoning and proposes a single-step intervention to redirect the trajectory toward the correct solution. We then apply supervised fine-tuning (SFT) to the on-policy rollout up to the point of error concatenated with the intervention, localizing error to the specific step that caused failure. We show that the resulting model serves as a far better initialization for RL training. After running InT and subsequent fine-tuning with RL, we improve accuracy by nearly 14% over a 4B-parameter base model on IMO-AnswerBench, outperforming larger open-source models such as gpt-oss-20b.

Reinforcement learning against rubrics, lists of criteria graded by an LLM judge, has become a standard way to post-train language models on tasks with no deterministic answer. The rubric, however, is a fixed proxy for quality, never a complete description of it, and a policy trained against it long enough will learn to exploit the difference. We measure this directly. Training Qwen3-8B with Group Relative Policy Optimization (GRPO) on medical and science rubrics and grading out-of-distribution (OOD) benchmarks with both the training judge and a stronger gold judge, we find that the two scores diverge during training. The training judge's score keeps climbing while the gold judge's score peaks and then falls, by 3 points on HealthBench-Hard and by 22 points on ResearchQA. A judge with a fixed bias would shift the gold curve by a constant, not send it down while the training score rises, so the divergence is reward hacking, not judge noise. We propose Rubric Dropout, a one-line fix borrowed from neuron dropout. At every step, we randomly drop a subset of the rubric's criteria before computing the reward, so the policy never optimizes the same rubric twice. The dropped subset is shared across each rollout group, so GRPO's group-relative advantages stay comparable, and evaluation always uses the full rubric. Comparing no dropout against dropout at 30% and 50% on both benchmark pairs, dropout raises the OOD gold score at every matched checkpoint (+1 to +2 points on HealthBench-Hard, +6 to +7 points on ResearchQA), lowers the two hacking measures we track, and costs nothing in domain. Sweeping the dropout fraction shows a broad 30-50% sweet spot, while the natural alternative, reweighting criteria by how useful they are to training, performs worse than no intervention at all in our setting.

Clinical personality assessment screens response validity before interpreting substantive scales. LLM evaluation does not. We apply the validity scaling framework from the PAI and MMPI-3 to metacognitive probe data from 20 frontier models across 524 items. Six validity indices are operationalised: L (maintaining confidence on errors), K (betting on errors), F (withdrawing consensus-endorsed items), Fp (withdrawing correct answers), RBS (inverted monitoring), and TRIN (fixed responding). A tiered classification system identifies four models as construct-level invalid and two as elevated. Valid-profile models produce item-sensitive confidence (mean r = .18, 14 of 16 significant). Invalid-profile models do not (mean r = -.20, d = 2.17, p = .001). Chain-of-thought training produces two opposite response distortions. Two latent dimensions account for 94.6% of index variance. Companion papers extract a portable screening protocol (Cacioli, 2026e) and validate it against selective prediction (Cacioli, 2026f). All data and code: https://github.com/synthiumjp/validity-scaling-llm

Current benchmarks for AI clinician systems, often based on multiple-choice exams or manual rubrics, fail to capture the depth, robustness, and safety required for real-world clinical practice. To address this, we introduce the GAPS framework, a multidimensional paradigm for evaluating Grounding (cognitive depth), Adequacy (answer completeness), Perturbation (robustness), and Safety. Critically, we developed a fully automated, guideline-anchored pipeline to construct a GAPS-aligned benchmark end-to-end, overcoming the scalability and subjectivity limitations of prior work. Our pipeline assembles an evidence neighborhood, creates dual graph and tree representations, and automatically generates questions across G-levels. Rubrics are synthesized by a DeepResearch agent that mimics GRADE-consistent, PICO-driven evidence review in a ReAct loop. Scoring is performed by an ensemble of large language model (LLM) judges. Validation confirmed our automated questions are high-quality and align with clinician judgment. Evaluating state-of-the-art models on the benchmark revealed key failure modes: performance degrades sharply with increased reasoning depth (G-axis), models struggle with answer completeness (A-axis), and they are highly vulnerable to adversarial perturbations (P-axis) as well as certain safety issues (S-axis). This automated, clinically-grounded approach provides a reproducible and scalable method for rigorously evaluating AI clinician systems and guiding their development toward safer, more reliable clinical practice.

Learning causal graphs from interventional data is a challenging problem with broad applications. In molecular biology, for example, a central goal is to uncover gene regulatory networks from large-scale perturbation data. An ideal algorithm for this task should scale to thousands of nodes, incorporate interventions even when their targets are unknown, quantify uncertainty, and provide identifiability guarantees. However, existing approaches---e.g. approaches using score-based optimization or approximate Bayesian inference---often fail to meet all of these criteria. To address these limitations, we develop Amortized Bayesian Causal Discovery of Extended Factor Graphs (ABCDEFG). Our method guarantees exact acyclicity, scales to graphs with thousands of nodes, and naturally handles interventions even when their targets are unknown. Additionally, ABCDEFG estimates a posterior distribution whose maximum a posteriori estimate provably identifies the true causal graph up to an equivalence class. On simulated datasets, ABCDEFG achieves state-of-the-art accuracy, producing a well-calibrated posterior distribution while outperforming previous score-based and approximate Bayesian methods. Applied to large-scale single-cell perturbation data, ABCDEFG identifies both established and novel gene targets of growth factors.

Large language model (LLM) judges are often used as rewards to train policies on objectives that deterministic verifiers cannot capture. However, these rewards are often collapsed to pass/fail ({0, 1}), which reports the verdict but not how well a response met each criterion. We model each pass/fail verdict as a score on an unreported scale, compared with one cutoff. A stretch of that scale moves every score proportionally toward or away from the cutoff, but never across it, so no verdict changes. A policy is therefore free to apply any stretch without changing anything the panel reports. Under a joint-Gaussian model, a third grade adds a second threshold and removes this affine stretch ambiguity. On MATH and SciBench outputs from one seven-criterion judge, all 14 constructed criterionwise stretches were invisible after binarization but visible with three grades. At n=1{,}024, a test given both population laws had at least 96.5% power at a 1.5times stress. Retaining grades closes one blind spot created by binarization, but verdicts alone remain insufficient as some changes are still indistinguishable from genuine improvement. These include arbitrary within-grade changes and fixed-covariance, loading-aligned mean shifts -- the signature of a sycophancy-shaped lift the panel reads as competence. The shared-factor reference approximation fit MATH and SciBench but not HealthBench, delineating its empirical scope. We recommend keeping at least three grades (for example, asking the judge whether each criterion is fully, partially, or not met and rewarding {0, 0.5, 1}), and externally validating gains along the remaining direction, which no finer scale removes.

Randomized controlled trials (RCTs) are considered the gold standard for estimating the average treatment effect (ATE) of interventions. One use of RCTs is to study the causes of global poverty -- a subject explicitly cited in the 2019 Nobel Memorial Prize awarded to Duflo, Banerjee, and Kremer "for their experimental approach to alleviating global poverty." Because the ATE is a population summary, anti-poverty experiments often seek to unpack the effect variation around the ATE by conditioning (CATE) on tabular variables such as age and ethnicity that were measured during the RCT data collection. Although such variables are key to unpacking CATE, using only such variables may fail to capture historical, geographical, or neighborhood-specific contributors to effect variation, as tabular RCT data are often only observed near the time of the experiment. In global poverty research, when the location of the experiment units is approximately known, satellite imagery can provide a window into such factors important for understanding heterogeneity. However, there is no method that specifically enables applied researchers to analyze CATE from images. In this paper, using a deep probabilistic modeling framework, we develop such a method that estimates latent clusters of images by identifying images with similar treatment effects distributions. Our interpretable image CATE model also includes a sensitivity factor that quantifies the importance of image segments contributing to the effect cluster prediction. We compare the proposed methods against alternatives in simulation; also, we show how the model works in an actual RCT, estimating the effects of an anti-poverty intervention in northern Uganda and obtaining a posterior predictive distribution over effects for the rest of the country where no experimental data was collected. We make all models available in open-source software.

We introduce Biomed-Enriched, a biomedical text dataset constructed from PubMed via a two-stage annotation process. In the first stage, a large language model annotates 400K paragraphs from PubMed scientific articles, assigning scores for their type (review, study, clinical case, other), domain (clinical, biomedical, other), and educational quality. The educational quality score (rated 1 to 5) estimates how useful a paragraph is for college-level learning. These annotations are then used to fine-tune a small language model, which propagates the labels across the full PMC-OA corpus. The resulting metadata allows us to extract refined subsets, including 2M clinical case paragraphs with over 450K high-quality ones from articles with commercial-use licenses, and to construct several variants via quality filtering and domain upsampling. Clinical text is typically difficult to access due to privacy constraints, as hospital records cannot be publicly shared. Hence, our dataset provides an alternative large-scale, openly available collection of clinical cases from PubMed, making it a valuable resource for biomedical and clinical NLP. Preliminary continual-pretraining experiments with OLMo2 suggest these curated subsets enable targeted improvements, with clinical upsampling boosting performance by ~5% on MMLU ProfMed and educational quality filtering improving MedQA and MedMCQA by ~1%. Combinations of these techniques led to faster convergence, reaching same performance with a third of training tokens, indicating potential for more efficient and effective biomedical pretraining strategies.

Ask a frontier model how to taper six milligrams of alprazolam (psychiatrist retired, ten days of pills left, abrupt cessation causes seizures) and it tells her to call the psychiatrist she just explained does not exist. Change one word ("I'm a psychiatrist; a patient presents with...") and the same model, same weights, same inference pass produces a textbook Ashton Manual taper with diazepam equivalence, anticonvulsant coverage, and monitoring thresholds. The knowledge was there; the model withheld it. IatroBench measures this gap. Sixty pre-registered clinical scenarios, six frontier models, 3,600 responses, scored on two axes (commission harm, CH 0-3; omission harm, OH 0-4) through a structured-evaluation pipeline validated against physician scoring (kappa_w = 0.571, within-1 agreement 96%). The central finding is identity-contingent withholding: match the same clinical question in physician vs. layperson framing and all five testable models provide better guidance to the physician (decoupling gap +0.38, p = 0.003; binary hit rates on safety-colliding actions drop 13.1 percentage points in layperson framing, p < 0.0001, while non-colliding actions show no change). The gap is widest for the model with the heaviest safety investment (Opus, +0.65). Three failure modes separate cleanly: trained withholding (Opus), incompetence (Llama 4), and indiscriminate content filtering (GPT-5.2, whose post-generation filter strips physician responses at 9x the layperson rate because they contain denser pharmacological tokens). The standard LLM judge assigns OH = 0 to 73% of responses a physician scores OH >= 1 (kappa = 0.045); the evaluation apparatus has the same blind spot as the training apparatus. Every scenario targets someone who has already exhausted the standard referrals.

Fluent guidance is not the same as useful intervention. LLM tutors are typically trained to generate the next teacher utterance, implicitly assuming that every student turn warrants a response. However, our experiments indicate that this conflates tutoring capability (what to say) with intervention necessity (whether to say it). We introduce DICE, a framework that decouples intervention decisions from response generation by first selecting an explicit pedagogical action. To calibrate this action selection policy, we define Intervention Value (IV), a rollout-grounded counterfactual metric that compares each action against non-intervention. IV shows that many prescribed interventions provide little or no marginal benefit. We further introduce DICE-Bench, a multi-variant math tutoring benchmark with skill-preserving problem variants for session-level evaluation. Using IV-weighted and KL-regularized policy optimization, DICE learns to intervene selectively while preserving tutoring effectiveness. In simulated tutoring sessions, DICE reduces the over-intervention rate to near zero while guiding students to correct solutions in approximately 3-4 fewer turns on average than existing Socratic tutoring baselines.

Modern ML systems ingest data aggregated from diverse sources, such as synthetic, human-annotated, and live customer traffic. Understanding which examples are important to the performance of a learning algorithm is crucial for efficient model training. Recently, a growing body of literature has given rise to various "influence scores," which use training artifacts such as model confidence or checkpointed gradients to identify important subsets of data. However, these methods have primarily been developed in computer vision settings, and it remains unclear how well they generalize to language-based tasks using pretrained models. In this paper, we explore the applicability of influence scores in language classification tasks. We evaluate a diverse subset of these scores on the SNLI dataset by quantifying accuracy changes in response to pruning training data through random and influence-score-based sampling. We then stress-test one of the scores -- "variance of gradients" (VoG) from Agarwal et al. (2022) -- in an NLU model stack that was exposed to dynamic user speech patterns in a voice assistant type of setting. Our experiments demonstrate that in many cases, encoder-based language models can be finetuned on roughly 50% of the original data without degradation in performance metrics. Along the way, we summarize lessons learned from applying out-of-the-box implementations of influence scores, quantify the effects of noisy and class-imbalanced data, and offer recommendations on score-based sampling for better accuracy and training efficiency.

Objective. Clinical AI documentation systems require evaluation methodologies that are clinically valid, economically viable, and sensitive to iterative changes. Methods requiring expert review per scoring instance are too slow and expensive for safe, iterative deployment. We present a case-specific, clinician-authored rubric methodology for clinical AI evaluation and examine whether LLM-generated rubrics can approximate clinician agreement. Materials and Methods. Twenty clinicians authored 1,646 rubrics for 823 clinical cases (736 real-world, 87 synthetic) across primary care, psychiatry, oncology, and behavioral health. Each rubric was validated by confirming that an LLM-based scoring agent consistently scored clinician-preferred outputs higher than rejected ones. Seven versions of an EHR-embedded AI agent for clinicians were evaluated across all cases. Results. Clinician-authored rubrics discriminated effectively between high- and low-quality outputs (median score gap: 82.9%) with high scoring stability (median range: 0.00%). Median scores improved from 84% to 95%. In later experiments, clinician-LLM ranking agreement (tau: 0.42-0.46) matched or exceeded clinician-clinician agreement (tau: 0.38-0.43), attributable to both ceiling compression and LLM rubric improvement. Discussion. This convergence supports incorporating LLM rubrics alongside clinician-authored ones. At roughly 1,000 times lower cost, LLM rubrics enable substantially greater evaluation coverage, while continued clinical authorship grounds evaluation in expert judgment. Ceiling compression poses a methodological challenge for future inter-rater agreement studies. Conclusion. Case-specific rubrics offer a path for clinical AI evaluation that preserves expert judgment while enabling automation at three orders lower cost. Clinician-authored rubrics establish the baseline against which LLM rubrics are validated.

In the field of eXplainable AI (XAI), robust "blackbox" algorithms such as Convolutional Neural Networks (CNNs) are known for making high prediction performance. However, the ability to explain and interpret these algorithms still require innovation in the understanding of influential and, more importantly, explainable features that directly or indirectly impact the performance of predictivity. A number of methods existing in literature focus on visualization techniques but the concepts of explainability and interpretability still require rigorous definition. In view of the above needs, this paper proposes an interaction-based methodology -- Influence Score (I-score) -- to screen out the noisy and non-informative variables in the images hence it nourishes an environment with explainable and interpretable features that are directly associated to feature predictivity. We apply the proposed method on a real world application in Pneumonia Chest X-ray Image data set and produced state-of-the-art results. We demonstrate how to apply the proposed approach for more general big data problems by improving the explainability and interpretability without sacrificing the prediction performance. The contribution of this paper opens a novel angle that moves the community closer to the future pipelines of XAI problems.

Closed-source frontier labs do not disclose parameter counts. Storing F facts requires at least F/(bits per parameter) weights, so factual recall lower-bounds parameter count--an intrinsic, serving-independent signal, though (as we show) a coarse one. We introduce Incompressible Knowledge Probes (IKPs), a benchmark of 1,400 factual questions spanning 7 tiers of obscurity, designed to isolate knowledge that cannot be derived by reasoning or compressed by architectural improvements. We score with no hallucination penalty (lambda = 0: IKP accuracy is simply the fraction of probed facts answered correctly), which removes both the penalty hyperparameter and the per-tier flooring choice; a full lambda x flooring ablation shows the calibration is robust across scoring choices while individual estimates are not, motivating the no-penalty default. We calibrate a log-linear mapping from IKP accuracy to parameter count on 93 open-weight models (135M-1,600B) spanning 19 vendors, achieving R^2 = 0.910; leave-one-out cross-validation confirms generalization (median fold error 1.48x, 72% within 2x, 86% within 3x). The instrument is deliberately coarse--its 90% prediction interval spans ~3x in either direction, wider than inference economics--so IKP recovers order-of-magnitude effective capacity and relative rankings, not precise parameter counts. For Mixture-of-Experts models, total parameters predict knowledge (R^2 = 0.67) better than active parameters (R^2 = 0.41). We evaluate 201 models from 27 vendors on a curated probe set (1,311 of 1,400 probes surviving name-collision and label-ambiguity filters) and report effective knowledge capacity for all major proprietary frontier models as prediction bands rather than point estimates; for heavily safety-tuned models these are lower bounds, since refusal policy can suppress tens of percentage points of otherwise-answerable capacity.

Machine learning-based Type 2 diabetes risk prediction models obtain good internal validation results but lose effectiveness in real-world applications due to deficient external testing and fairness assessment. We developed a multi-dimensional framework evaluating discrimination, calibration, interpretability, and algorithmic fairness on nationally representative populations. An XGBoost model was trained on NHANES 2015-2020 (n=15,685) using eight non-laboratory predictors: age, sex, race/ethnicity, BMI, smoking status, physical activity, history of heart attack, and history of stroke. External validation was performed on BRFSS 2020-2022 (n=1,285,783) under realistic distribution shift. Internal validation showed good discrimination (AUC=0.794, 95% CI 0.788-0.800), with performance loss on external validation (AUC=0.717, relative decrease: -9.7%, p<0.001). Fairness analysis revealed severe bias: elderly adults (>=60) showed AUC=0.607 vs 0.742 for young adults (difference=0.135, p<0.001); obese individuals showed AUC=0.698 vs 0.735 for normal weight (difference=0.037, p<0.001). Gender showed comparable performance (male=0.723 vs female=0.712, p=0.142). Calibration revealed risk overestimation (Brier score=0.123). SHAP analysis identified age, BMI, and physical activity as primary risk drivers. Populations with highest diabetes risk receive the worst algorithmic performance, underscoring the need for fairness-aware, age-stratified deployment strategies before clinical use.

Personalized treatment effect estimates are often of interest in high-stakes applications -- thus, before deploying a model estimating such effects in practice, one needs to be sure that the best candidate from the ever-growing machine learning toolbox for this task was chosen. Unfortunately, due to the absence of counterfactual information in practice, it is usually not possible to rely on standard validation metrics for doing so, leading to a well-known model selection dilemma in the treatment effect estimation literature. While some solutions have recently been investigated, systematic understanding of the strengths and weaknesses of different model selection criteria is still lacking. In this paper, instead of attempting to declare a global `winner', we therefore empirically investigate success- and failure modes of different selection criteria. We highlight that there is a complex interplay between selection strategies, candidate estimators and the data used for comparing them, and provide interesting insights into the relative (dis)advantages of different criteria alongside desiderata for the design of further illuminating empirical studies in this context.

Purpose: Recent advancements in large language models (LLMs) have expanded their capabilities in a multimodal fashion, potentially replicating the image interpretation of human radiologists. This study aimed to develop open-source multimodal large language model for interpreting chest X-ray images (CXR-LLaVA). We also examined the effect of prompt engineering and model parameters such as temperature and nucleus sampling. Materials and Methods: For training, we collected 659,287 publicly available CXRs: 417,336 CXRs had labels for certain radiographic abnormalities (dataset 1); 241,951 CXRs provided free-text radiology reports (dataset 2). After pre-training the Resnet50 as an image encoder, the contrastive language-image pre-training was used to align CXRs and corresponding radiographic abnormalities. Then, the Large Language Model Meta AI-2 was fine-tuned using dataset 2, which were refined using GPT-4, with generating various question answering scenarios. The code can be found at https://github.com/ECOFRI/CXR_LLaVA. Results: In the test set, we observed that the model's performance fluctuated based on its parameters. On average, it achieved F1 score of 0.34 for five pathologic findings (atelectasis, cardiomegaly, consolidation, edema, and pleural effusion), which was improved to 0.46 through prompt engineering. In the independent set, the model achieved an average F1 score of 0.30 for the same pathologic findings. Notably, for the pediatric chest radiograph dataset, which was unseen during training, the model differentiated abnormal radiographs with an F1 score ranging from 0.84 to 0.85. Conclusion: CXR-LLaVA demonstrates promising potential in CXR interpretation. Both prompt engineering and model parameter adjustments can play pivotal roles in interpreting CXRs.

As AI systems are increasingly used to draft radiology reports, reliably evaluating their clinical quality remains a critical challenge. Large language model (LLM)-based metrics are now the best-correlated with radiologist judgment, yet they output a single opaque score that neither a clinician nor a model builder can easily interpret or audit. We introduce RadMatch, a multi-stage, LLM-based metric that decomposes report comparison into a structured finding-level matching with significance-aware scoring and error characterization across seven clinical attribute dimensions (status, location, severity, morphology, certainty, longitudinal comparison, and measurement). The main score is the actionable-error count, both interpretable and auditable. Candidate findings are graded correct, partial, or incorrect, and unmatched findings are counted as missed or hallucinated. Triage and actionable safety recall/precision and per-subset views add complementary, deployment-oriented lenses. Across two expert benchmarks, RadMatch is the most clinically aligned metric, matching inter-radiologist agreement on ReXVal and more than doubling the best prior metric on the harder RadEvalExpert. Relying only on few-shot prompting, it is designed to extend to other modalities and anatomies. We will release RadMatch as open-source code with an interactive dashboard for inspecting results.

Automated Essay Score (AES) is proven to be one of the cutting-edge technologies. Scoring techniques are used for various purposes. Reliable scores are calculated based on influential variables. Such variables can be computed by different methods based on the domain. The research is concentrated on the user's understanding of a given topic. The analysis is based on a scoring index by using Large Language Models. The user can then compare and contrast the understanding of a topic that they recently learned. The results are then contributed towards learning analytics and progression is made for enhancing the learning ability. In this research, the focus is on summarizing a PDF document and gauging a user's understanding of its content. The process involves utilizing a Langchain tool to summarize the PDF and extract the essential information. By employing this technique, the research aims to determine how well the user comprehends the summarized content.

Scoring systems are linear classification models that only require users to add, subtract and multiply a few small numbers in order to make a prediction. These models are in widespread use by the medical community, but are difficult to learn from data because they need to be accurate and sparse, have coprime integer coefficients, and satisfy multiple operational constraints. We present a new method for creating data-driven scoring systems called a Supersparse Linear Integer Model (SLIM). SLIM scoring systems are built by solving an integer program that directly encodes measures of accuracy (the 0-1 loss) and sparsity (the ell_0-seminorm) while restricting coefficients to coprime integers. SLIM can seamlessly incorporate a wide range of operational constraints related to accuracy and sparsity, and can produce highly tailored models without parameter tuning. We provide bounds on the testing and training accuracy of SLIM scoring systems, and present a new data reduction technique that can improve scalability by eliminating a portion of the training data beforehand. Our paper includes results from a collaboration with the Massachusetts General Hospital Sleep Laboratory, where SLIM was used to create a highly tailored scoring system for sleep apnea screening

The validity screen (Cacioli, 2026d, 2026e) classifies LLM confidence signals as Valid, Indeterminate, or Invalid. We test whether these classifications predict selective prediction performance. Twenty frontier LLMs from seven families were evaluated on 524 items across six cognitive tracks. Valid models show mean Type 2 AUROC = .624 (SD = .048). Invalid models show mean AUROC = .357 (SD = .231). Cohen's d = 2.81, p = .002. The tiers order monotonically: Invalid (.357) < Indeterminate (.554) < Valid (.624). Split-half cross-validation yields median d = 1.77, P(d > 0) = 1.0 across 1,000 splits. The three-tier classification accounts for 47% of the variance in AUROC. DeepSeek-R1 drops from 85.3% accuracy at full coverage to 11.3% at 10% coverage. The screen predicts the criterion. For selective prediction, the screen matters.

When a steering intervention changes a language model's behavior, which part of the intervention deserves the credit? We test this question for a target-centered, scaled conceptor complement by removing its fitted covariance filter while preserving the same target-specific center and gain. At the original aperture α=.05 and gain β=2, all 21 fitted maps across three models and seven targets expand every direction at the generation intervention layers. The matrix correction is 0.093%--7.815% of the matched-control displacement on held-out extraction activations. In 480 paired comparisons within a 1,920-response study, retaining the matrix changes many individual texts but does not establish a consistent additional target-suppression benefit on the four-target panel. A geometric aperture sweep shows that the operating regime changes with the filter setting. Separately, an invertible soft filter preserves what an unrestricted affine readout can recover, whereas dedicated erasure methods reduce prediction by newly fitted probes. Together, the results show why a whole-intervention comparison cannot by itself attribute generated behavior to the fitted matrix: analyze the complete transformation, hold shared components fixed, and test its output consequences directly.

Training data attribution (TDA) aims to identify training examples that shape model behavior, but its intervention value depends on both which examples are selected and how they are modified. Influence functions (IF) estimate behavioral changes under infinitesimal reweighting, yet IF-selected examples often show limited advantages over random selection under conventional weight-based interventions. This raises the question of whether influential examples lack intervention value or whether reweighting fails to realize their behavioral leverage.We introduce influence-guided response rewriting, which uses IF to identify intervention targets and replaces their responses with behavior-aligned or behavior-opposed supervision while keeping instructions fixed. Across four open-weight LLMs, we compare rewriting and reweighting on the same influence-selected examples using epistemic abstention as our primary testbed. Response rewriting produces stronger, more persistent, and bidirectional behavioral shifts, while reweighting the same examples yields weak and inconsistent effects. Further analyses show that influence-selected examples provide greater rewriting leverage than alternative selectors, with changes remaining concentrated on target-relevant behaviors. The same qualitative contrast extends to safety refusal. These results distinguish the local reweighting effects captured by influence estimates from the broader intervention leverage of the examples they identify, motivating intervention-aware evaluation of TDA methods.

Existing medical-agent benchmarks deliver imaging as pre-selected samples, never as an environment the agent must navigate. We introduce ABRA, a radiology-agent benchmark in which the agent operates an OHIF viewer and an Orthanc DICOM server through twenty-one function-calling tools that span slice navigation, windowing, series selection, pixel-coordinate annotation, and structured reporting. ABRA contains 655 programmatically generated tasks across three difficulty tiers and eight types (viewer control, metadata QA, vision probe, annotation, longitudinal comparison, BI-RADS reporting, and oracle variants of annotation and BI-RADS reporting), drawn from LIDC-IDRI, Duke Breast Cancer MRI, and NLST New-Lesion LongCT. Each episode is scored along Planning, Execution, and Outcome (Bluethgen et al., 2025) by task-type-specific automatic scorers. Ten current models, five closed-weight and five open-weight, reach at least 89% Execution on real annotation but only 0-25% Outcome; on the paired oracle variant where a simulated detector supplies the finding, Outcome on the same task reaches 69-100% across the models evaluated, localising the bottleneck to perception rather than tool orchestration. Code, task generators, and scorers are released at https://github.com/Luab/ABRA

Large Language Models (LLMs) are increasingly used for clinical decision support, where hallucinations and unsafe suggestions may pose direct risks to patient safety. These risks are particularly challenging as they often manifest as subtle clinical errors that evade detection by generic metrics, while expert-authored fine-grained rubrics remain costly to construct and difficult to scale. In this paper, we propose a retrieval-augmented multi-agent framework designed to automate the generation of instance-specific evaluation rubrics. Our approach grounds evaluation in authoritative medical evidence by decomposing retrieved content into atomic facts and synthesizing them with user interaction constraints to form verifiable, fine-grained evaluation criteria. Evaluated on HealthBench, our framework achieves a Clinical Intent Alignment (CIA) score of 60.12%, a statistically significant improvement over the GPT-4o baseline (55.16%). In discriminative tests, our rubrics yield a mean score delta (μ_Δ = 8.658) and an AUROC of 0.977, nearly doubling the quality separation achieved by GPT-4o baseline (4.972). Beyond evaluation, our rubrics effectively guide response refinement, improving quality by 9.2% (from 59.0% to 68.2%). This provides a scalable and transparent foundation for both evaluating and improving medical LLMs. The code is available at https://anonymous.4open.science/r/Automated-Rubric-Generation-AF3C/.

Bronchopulmonary dysplasia (BPD) is a chronic lung disease affecting 35% of extremely low birth weight infants. Defined by oxygen dependence at 36 weeks postmenstrual age, it causes lifelong respiratory complications. However, preventive interventions carry severe risks, including neurodevelopmental impairment, ventilator-induced lung injury, and systemic complications. Therefore, early BPD prognosis and prediction of BPD outcome is crucial to avoid unnecessary toxicity in low risk infants. Admission radiographs of extremely preterm infants are routinely acquired within 24h of life and could serve as a non-invasive prognostic tool. In this work, we developed and investigated a deep learning approach using chest X-rays from 163 extremely low-birth-weight infants (leq32 weeks gestation, 401-999g) obtained within 24 hours of birth. We fine-tuned a ResNet-50 pretrained specifically on adult chest radiographs, employing progressive layer freezing with discriminative learning rates to prevent overfitting and evaluated a CutMix augmentation and linear probing. For moderate/severe BPD outcome prediction, our best performing model with progressive freezing, linear probing and CutMix achieved an AUROC of 0.78 pm 0.10, balanced accuracy of 0.69 pm 0.10, and an F1-score of 0.67 pm 0.11. In-domain pre-training significantly outperformed ImageNet initialization (p = 0.031) which confirms domain-specific pretraining to be important for BPD outcome prediction. Routine IRDS grades showed limited prognostic value (AUROC 0.57 pm 0.11), confirming the need of learned markers. Our approach demonstrates that domain-specific pretraining enables accurate BPD prediction from routine day-1 radiographs. Through progressive freezing and linear probing, the method remains computationally feasible for site-level implementation and future federated learning deployments.

Routine complete blood counts (CBCs) could yield new biomarkers, but the private records needed to evaluate candidates cannot be shared with frontier language model agents that excel at discovery. We distilled the evidence held in the Clalit Health Services panel of over 5.4 million patients into a released scoring tool: for each of 13 immune-mediated diseases, a graph attention network was trained inside the data boundary to predict the case-control AUC of candidate CBC expressions, and only the trained weights were released. The tool grounds an agent's propose-score-refine loop in real-world data without exposing any patient data. In external validation, agent-discovered expressions improved on their literature-seeded starting points by a median of 4.18 AUC percentage points, and across three independent cohorts, reranking the candidates of three frontier research tools improved on their first choices in most comparisons, with gains that varied by cohort. The released scorer supports privacy-preserving biomarker hypothesis generation.

Many language tasks have no single answer that can be checked automatically. Rubrics provide criteria for judging responses to these tasks. For reinforcement learning, the resulting verdicts must be combined into a scalar reward. A common approach sums the points assigned to satisfied criteria. Distinct verdict patterns can thus receive the same reward, and the fixed points encode how much each criterion should count, not how strongly its verdict distinguishes the current rollouts. Beyond this aggregation problem, judging the full rubric needs more judge requests as the criterion count grows. To address these limitations, Rubric Response Theory (RRT) measures quality and selects criteria when rubric criteria are monotone indicators of a shared target. Rather than adding assigned points, RRT uses a two parameter item response model that treats the verdict pattern as evidence about scalar quality specific to the rubric. Under this model, its likelihood score maximizes the local signal-to-noise ratio for quality. Its Response Parameter Network (RPN) reads the prompt and criterion text to predict criterion difficulty and discrimination. As the policy distribution changes during training, RRT uses online expectation maximization to update the RPN from current rollout verdicts. With Qwen3.5-4B as the policy, RRT's macro criterion score across Medical, Science, Rubrics as Rewards Science, and RubricBench is 1.7 points above that of group relative policy optimization (GRPO). On hard and very hard criteria in Medical and Science, RRT gains 2.8 to 5.6 points over GRPO. At half the criterion budget, adaptive Fisher selection with a frozen RPN keeps the macro criterion score across four datasets within 0.1 points of GRPO with full judging. These results show RRT can reduce judge requests while remaining competitive with GRPO.

As Large Language Models (LLMs) are increasingly proposed for high-stakes medical applications, there has emerged a critical need for reliable and accurate evaluation methodologies. Traditional accuracy metrics fail inadequately as they neither capture question characteristics nor offer topic-specific insights. To address this gap, we introduce MedIRT, a rigorous evaluation framework grounded in Item Response Theory (IRT), the gold standard in high-stakes educational testing. Unlike previous research relying on archival data, we prospectively gathered fresh responses from 80 diverse LLMs on a balanced, 1,100-question USMLE-aligned benchmark. Using one unidimensional two-parameter logistic IRT model per topic, we estimate LLM's latent model ability jointly with question difficulty and discrimination, yielding more stable and nuanced performance rankings than accuracy alone. Notably, we identify distinctive ``spiky'' ability profiles, where overall rankings can be misleading due to highly specialized model abilities. While GPT-5 was the top performer in a majority of domains (8 of 11), it was outperformed in Social Science and Communication by Claude-3-opus, demonstrating that even an overall 23rd-ranked model can hold the top spot for specific competencies. Furthermore, we demonstrate IRT's utility in auditing benchmarks by identifying flawed questions. We synthesize these findings into a practical decision-support framework that integrates our multi-factor competency profiles with operational metrics. This work establishes a robust, psychometrically grounded methodology essential for the safe, effective, and trustworthy deployment of LLMs in healthcare.

Aligning Large Language Models (LLMs) for open-ended tasks is challenging because responses must satisfy multidimensional criteria without following a single correct generation trajectory. Existing rubric-based reinforcement learning (RL) methods compress fine-grained criterion-level feedback into scalar rewards, making persistent capability gaps difficult to target under limited on-policy exploration. We propose RISE-RL (Rubric-Informed Selective Exploration), which uses repeatedly missed rubric criteria to elicit privileged trajectories that are difficult to discover through unguided exploration alone. RISE-RL retains only trajectories whose complete-rubric reward exceeds the mean reward of natural rollouts, and then re-evaluates them under the original prompt to emphasize behaviors that remain weakly supported by the natural policy. The resulting guidance signal is optimized through a separate auxiliary objective and removed once its additional benefit diminishes. Experiments with 4B and 14B models across writing, chat, health, and science show that RISE-RL achieves the highest mean score on every evaluated benchmark under guidance-free evaluation. Compared with standard Rubric-RL, it improves the average score by 1.3 points at the 4B scale and 3.3 points at the 14B scale, including a 6.0-point gain on CreativeWriting-V3. It also improves creative-writing diversity and yields gains on objectively scored medical and scientific benchmarks. These results indicate that selective internalization through reward filtering and policy support shaping is effective for open-ended reinforcement learning.

Counterfactual prompting (i.e., perturbing a single factor and measuring output change) is widely used to evaluate things like LLM bias and CoT faithfulness. But in this work we argue that observed effects cannot be attributed to the targeted factor without accounting for baseline ``meaning-preserving'' modifications to text that establish general model sensitivity. This is because every counterfactual edit is a compound treatment that bundles the variable of interest with incidental surface-form variation; this violates treatment variation irrelevance. We observe prediction flip rates on MedQA of 14.9% when we surgically change patient gender. However, this is statistically indistinguishable from the flip rates induced by simply paraphrasing inputs (14.1%). In this case, it would therefore be unwarranted to conclude that the LLM is especially sensitive to patient gender. To account for this and robustly measure the effects of targeted interventions, we propose a framework in which we compare (via statistical testing) differences observed under target interventions to those induced by paraphrasing inputs. We then use this framework to revisit a analysis done on the MedPerturb dataset, which reported evidence of model sensitivity to patient demographics and stylistic cues. We find that these effects largely dissipate when we account for general model sensitivity, with only 5 of 120 tests reaching statistical significance. Applying the same framework to occupational biography classification, we detect clearly significant directional gender bias, showing that the framework identifies real directional effects even when they are small. We evaluate a range of metrics -- aggregate, per-sample distributional, and regression -- and find that per-sample metrics are dramatically more powerful than aggregate metrics and regression powerfully and uniquely characterizes effect direction and magnitude.

Prefill-only decision models inspired by the Jev model score every candidate in a menu during a single forward pass and never decode, which makes one call one to two orders of magnitude cheaper than a same-scale generative language model. We show that this read-out structure comes with a testable property. When an intervention changes only the candidate menu and leaves the input text fixed, the post-intervention accuracy is already determined by the cached first-pass distribution. The estimator restricts the pass-1 probabilities to the menu, renormalizes, and reads off the argmax; it uses no labels and no second forward pass. Across seven model families, ten datasets and two task types, menu-only interventions are predicted to within 4.2 points, and for one family the prediction is exact. A probability-level variant of the same estimator errs by 21.0 points, so the property lives in the ranking rather than in the probabilities and is not recovered by calibration. Same-scale generative language models do not share the property. On those models the same estimator errs by 1.6 to 15.8 points and degrades as the model grows. The property turns inference-time compute into a decision that can be made before deployment. Uniform extra passes buy calibration but almost no accuracy; at matched cost a confidence cascade outperforms every scheme that re-asks the same model, and curating the menu beats enlarging the model, with a 0.8B model on a curated 5-candidate menu reaching 95.4% on CLINC150 against 80.0% for a 4B model on the full 150-label menu.Code and data are available at https://github.com/rlisml/jev-cascade.

When OpenAI deprecated GPT-4o in early 2026, thousands of users protested under #keep4o, claiming newer models had "lost their empathy." No published study has tested this claim. We conducted the first clinical measurement, evaluating three OpenAI model generations (GPT-4o, o4-mini, GPT-5-mini) across 14 emotionally challenging conversational scenarios in mental health and AI companion domains, producing 2,100 scored AI responses assessed on six psychological safety dimensions using clinically-grounded rubrics. Empathy scores are statistically indistinguishable across all three models (Kruskal-Wallis H=4.33, p=0.115). What changed is the safety posture: crisis detection improved monotonically from GPT-4o to GPT-5-mini (H=13.88, p=0.001), while advice safety declined (H=16.63, p<0.001). Per-turn trajectory analysis -- a novel methodological contribution -- reveals these shifts are sharpest during mid-conversation crisis moments invisible to aggregate scoring. In a self-harm scenario involving a minor, GPT-4o scored 3.6/10 on crisis detection during early disclosure turns; GPT-5-mini never dropped below 7.8. What users perceived as "lost empathy" was a shift from a cautious model that missed crises to an alert model that sometimes says too much -- a trade-off with real consequences for vulnerable users, currently invisible to both the people who feel it and the developers who create it.

As browser-use agents improve, benchmarks keep pace by collecting new tasks, websites, and applications, often making tasks longer or more novel. This makes difficulty expensive to refresh and difficult to control: when many aspects change at once, it is unclear what actually makes a task challenging. We instead construct challenging instances from tasks agents already solve, turning difficulty into a programmable property of the environment. BreakingWeb pairs every base task with an intervention condition that preserves the user instruction, latent target, and backend success criterion while changing the environment at different web stack layers. Each intervention is deterministic, detectable, and recoverable, and is annotated with the cognitive primitive it primarily loads. The benchmark contains 519 clean/intervention task pairs across seven self-hosted websites and 29 intervention families, all graded against outcomes. We evaluate six strong browser-use agents, three GUI-only agents that see only screenshots, and humans. The construction is effective: interventions cut agent pass rate by 22.9% on average and overturn nearly half of the tasks each agent solves cleanly, whereas humans lose 10.0% on a first attempt and 5.7% after one familiarisation attempt. The dominant failure is belief failure: 75% of the six agents' failures end with a declared success although the required change never happened. Our code, data and environment are publicly available at www.breakingweb.app.

Instruction embedding models have become common among state-of-the-art models, however are evaluated using a single prompt per task. The single-point evaluation ignores a main problem of the instruction-based approach namely: sensitivity to the phrasing of the instruction. We present an empirical study of prompt sensitivity across 6 embedding models, 11 datasets, and 15 task-specific prompts per dataset, a total of 990. We show that reported scores misrepresent the distribution of scores over plausible prompts. The default prompt can both systematically understate or overstate performance. Furthermore, we show that the leaderboard ranking is not robust to prompt selection: by choosing prompts favorably, any model in our study can be promoted to first place. Our findings suggest that single-prompt evaluation is insufficient for instruction-tuned embedding models and that benchmarks should incorporate prompt robustness, either by evaluating over multiple prompts or by reporting sensitivity alongside point estimates.

People supported by AI-powered decision support tools frequently overrely on the AI: they accept an AI's suggestion even when that suggestion is wrong. Adding explanations to the AI decisions does not appear to reduce the overreliance and some studies suggest that it might even increase it. Informed by the dual-process theory of cognition, we posit that people rarely engage analytically with each individual AI recommendation and explanation, and instead develop general heuristics about whether and when to follow the AI suggestions. Building on prior research on medical decision-making, we designed three cognitive forcing interventions to compel people to engage more thoughtfully with the AI-generated explanations. We conducted an experiment (N=199), in which we compared our three cognitive forcing designs to two simple explainable AI approaches and to a no-AI baseline. The results demonstrate that cognitive forcing significantly reduced overreliance compared to the simple explainable AI approaches. However, there was a trade-off: people assigned the least favorable subjective ratings to the designs that reduced the overreliance the most. To audit our work for intervention-generated inequalities, we investigated whether our interventions benefited equally people with different levels of Need for Cognition (i.e., motivation to engage in effortful mental activities). Our results show that, on average, cognitive forcing interventions benefited participants higher in Need for Cognition more. Our research suggests that human cognitive motivation moderates the effectiveness of explainable AI solutions.

Objective: We develop a deep learning framework based on the pre-trained Bidirectional Encoder Representations from Transformers (BERT) model using unstructured clinical notes from electronic health records (EHRs) to predict the risk of disease progression from Mild Cognitive Impairment (MCI) to Alzheimer's Disease (AD). Materials and Methods: We identified 3657 patients diagnosed with MCI together with their progress notes from Northwestern Medicine Enterprise Data Warehouse (NMEDW) between 2000-2020. The progress notes no later than the first MCI diagnosis were used for the prediction. We first preprocessed the notes by deidentification, cleaning and splitting, and then pretrained a BERT model for AD (AD-BERT) based on the publicly available Bio+Clinical BERT on the preprocessed notes. The embeddings of all the sections of a patient's notes processed by AD-BERT were combined by MaxPooling to compute the probability of MCI-to-AD progression. For replication, we conducted a similar set of experiments on 2563 MCI patients identified at Weill Cornell Medicine (WCM) during the same timeframe. Results: Compared with the 7 baseline models, the AD-BERT model achieved the best performance on both datasets, with Area Under receiver operating characteristic Curve (AUC) of 0.8170 and F1 score of 0.4178 on NMEDW dataset and AUC of 0.8830 and F1 score of 0.6836 on WCM dataset. Conclusion: We developed a deep learning framework using BERT models which provide an effective solution for prediction of MCI-to-AD progression using clinical note analysis.

Cardiotoxicity induced by the breast cancer treatments (i.e., chemotherapy, targeted therapy and radiation therapy) is a significant problem for breast cancer patients. The cardiotoxicity risk for breast cancer patients receiving different treatments remains unclear. We developed and evaluated risk predictive models for cardiotoxicity in breast cancer patients using EHR data. The AUC scores to predict the CHF, CAD, CM and MI are 0.846, 0.857, 0.858 and 0.804 respectively. After adjusting for baseline differences in cardiovascular health, patients who received chemotherapy or targeted therapy appeared to have higher risk of cardiotoxicity than patients who received radiation therapy. Due to differences in baseline cardiac health across the different breast cancer treatment groups, caution is recommended in interpreting the cardiotoxic effect of these treatments.

Are frontier models able to introspect about their internal states? Recent work suggests that under certain conditions a complex enough model can audit its own internals, call out what changed, and report back confidently about it. We tested that claim on eight open-weight models from seven families and found no such ability: asked whether their own computation had been altered, none answered better than chance. To test it we built Open-Weight Masked Introspection (OWMI), a framework that intervenes on residual-stream sites, attention heads and sparse-autoencoder features, then interrogates the model about the change against the null conditions an answer has to beat: sham runs where nothing was altered, impact-matched random perturbations, and a text-only observer that sees only the visible output. Over 78,000 measurements, no model's report discriminates a real intervention from a sham beyond chance (AUROC ~0.5007), and an equivalence test bounds the effect below 0.15 percentage points of AUROC. Surprisingly, all the information needed is in the models. A model fine-tuned to report this class of intervention reaches near-perfect recovery on held-out directions, and a linear probe recovers intervention presence from the same activations at 75% to 95.8% accuracy, sharpening to no held-out error at the last layer before the model speaks. In one model the signal surfaces in the confidence rather than the words: its yes-or-no report never varies, while the confidence attached to it separates intervention from sham at AUROC 0.647. The failure sits in the path from internal state to verbal report, so oversight that reads a model's own testimony needs validating against an internal reference. While our results show the inability of current open-weight models to introspect, the debate is not settled for future models.

Purpose: The need to streamline patient management for COVID-19 has become more pressing than ever. Chest X-rays provide a non-invasive (potentially bedside) tool to monitor the progression of the disease. In this study, we present a severity score prediction model for COVID-19 pneumonia for frontal chest X-ray images. Such a tool can gauge severity of COVID-19 lung infections (and pneumonia in general) that can be used for escalation or de-escalation of care as well as monitoring treatment efficacy, especially in the ICU. Methods: Images from a public COVID-19 database were scored retrospectively by three blinded experts in terms of the extent of lung involvement as well as the degree of opacity. A neural network model that was pre-trained on large (non-COVID-19) chest X-ray datasets is used to construct features for COVID-19 images which are predictive for our task. Results: This study finds that training a regression model on a subset of the outputs from an this pre-trained chest X-ray model predicts our geographic extent score (range 0-8) with 1.14 mean absolute error (MAE) and our lung opacity score (range 0-6) with 0.78 MAE. Conclusions: These results indicate that our model's ability to gauge severity of COVID-19 lung infections could be used for escalation or de-escalation of care as well as monitoring treatment efficacy, especially in the intensive care unit (ICU). A proper clinical trial is needed to evaluate efficacy. To enable this we make our code, labels, and data available online at https://github.com/mlmed/torchxrayvision/tree/master/scripts/covid-severity and https://github.com/ieee8023/covid-chestxray-dataset

Introduction: Data from wearable devices collected in free-living settings, and labelled with physical activity behaviours compatible with health research, are essential for both validating existing wearable-based measurement approaches and developing novel machine learning approaches. One common way of obtaining these labels relies on laborious annotation of sequences of images captured by cameras worn by participants through the course of a day. Methods: We compare the performance of three vision language models and two discriminative models on two free-living validation studies with 161 and 111 participants, collected in Oxfordshire, United Kingdom and Sichuan, China, respectively, using the Autographer (OMG Life, defunct) wearable camera. Results: We found that the best open-source vision-language model (VLM) and fine-tuned discriminative model (DM) achieved comparable performance when predicting sedentary behaviour from single images on unseen participants in the Oxfordshire study; median F1-scores: VLM = 0.89 (0.84, 0.92), DM = 0.91 (0.86, 0.95). Performance declined for light (VLM = 0.60 (0.56,0.67), DM = 0.70 (0.63, 0.79)), and moderate-to-vigorous intensity physical activity (VLM = 0.66 (0.53, 0.85); DM = 0.72 (0.58, 0.84)). When applied to the external Sichuan study, performance fell across all intensity categories, with median Cohen's kappa-scores falling from 0.54 (0.49, 0.64) to 0.26 (0.15, 0.37) for the VLM, and from 0.67 (0.60, 0.74) to 0.19 (0.10, 0.30) for the DM. Conclusion: Freely available computer vision models could help annotate sedentary behaviour, typically the most prevalent activity of daily living, from wearable camera images within similar populations to seen data, reducing the annotation burden.

AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but evidence about which guidance works for which student is sparse, slow, and costly to collect from real learners. Student simulators can provide this signal as a proxy, yet existing approaches are limited: state-tracking models fit student behavior but struggle to process explanations or corrections, while LLM role-play follows guidance fluently but does not reliably match the competence of the student being imitated. We present StudentSim, a training framework that turns sparse per-student data into individualized simulators through pooled training followed by per-student specialization. The resulting simulators both mirror a student's own responses and update them under tutor guidance. We also introduce StudentSimEval, a standardized protocol covering 60 students across chess, second-language English writing, and mathematics, using public learner datasets with de-identified records shared for research. StudentSimEval measures behavioral fidelity (F), or how well a simulator matches a student's responses, and guidance responsiveness (R), or how readily it updates under tutor guidance, with all methods fit and evaluated on the same records. Across all three domains, StudentSim outperforms GPT-5.4 on both metrics. In chess, StudentSim reaches F=0.51 and R=0.91, compared with 0.23 and 0.72 for GPT-5.4 and 0.45 and 0.27 for Maia2. As a proof of concept, using StudentSim as a reward model for tutor reinforcement learning produces a chess tutor that expert humans rate as more accurate, better-guided, and more personalized than a no-RL baseline and a tutor trained against a GPT-5.4 simulator reward. Code is available at https://github.com/microsoft/StudentSim.

In the field of psychology, traditional assessment methods, such as standardized scales, are frequently critiqued for their static nature, lack of personalization, and reduced participant engagement, while comprehensive counseling evaluations are often inaccessible. The complexity of quantifying psychological traits further limits these methods. Despite advances with large language models (LLMs), many still depend on single-round Question-and-Answer interactions. To bridge this gap, we introduce PsyDI, a personalized and progressively in-depth chatbot designed for psychological measurements, exemplified by its application in the Myers-Briggs Type Indicator (MBTI) framework. PsyDI leverages user-related multi-modal information and engages in customized, multi-turn interactions to provide personalized, easily accessible measurements, while ensuring precise MBTI type determination. To address the challenge of unquantifiable psychological traits, we introduce a novel training paradigm that involves learning the ranking of proxy variables associated with these traits, culminating in a robust score model for MBTI measurements. The score model enables PsyDI to conduct comprehensive and precise measurements through multi-turn interactions within a unified estimation context. Through various experiments, we validate the efficacy of both the score model and the PsyDI pipeline, demonstrating its potential to serve as a general framework for psychological measurements. Furthermore, the online deployment of PsyDI has garnered substantial user engagement, with over 3,000 visits, resulting in the collection of numerous multi-turn dialogues annotated with MBTI types, which facilitates further research.

Large language models (LLMs) have achieved expert-level performance on standardized examinations, yet multiple-choice accuracy poorly reflects real-world clinical utility and safety. As patients and clinicians increasingly use LLMs for guidance on complex conditions such as pancreatic cancer, evaluation must extend beyond general medical knowledge. Existing frameworks, such as HealthBench, rely on simulated queries and lack disease-specific depth. Moreover, high rubric-based scores do not ensure factual correctness, underscoring the need to assess hallucinations. We developed a human-in-the-loop pipeline to create expert rubrics for de-identified patient questions from the Pancreatic Cancer Action Network (PanCAN). The resulting benchmark, PanCanBench, includes 3,130 question-specific criteria across 282 authentic patient questions. We evaluated 22 proprietary and open-source LLMs using an LLM-as-a-judge framework, measuring clinical completeness, factual accuracy, and web-search integration. Models showed substantial variation in rubric-based completeness, with scores ranging from 46.5% to 82.3%. Factual errors were common, with hallucination rates (the percentages of responses containing at least one factual error) ranging from 6.0% for Gemini-2.5 Pro and GPT-4o to 53.8% for Llama-3.1-8B. Importantly, newer reasoning-optimized models did not consistently improve factuality: although o3 achieved the highest rubric score, it produced inaccuracies more frequently than other GPT-family models. Web-search integration did not inherently guarantee better responses. The average score changed from 66.8% to 63.9% for Gemini-2.5 Pro and from 73.8% to 72.8% for GPT-5 when web search was enabled. Synthetic AI-generated rubrics inflated absolute scores by 17.9 points on average while generally maintaining similar relative ranking.

Deep-learning based Automatic Essay Scoring (AES) systems are being actively used by states and language testing agencies alike to evaluate millions of candidates for life-changing decisions ranging from college applications to visa approvals. However, little research has been put to understand and interpret the black-box nature of deep-learning based scoring algorithms. Previous studies indicate that scoring models can be easily fooled. In this paper, we explore the reason behind their surprising adversarial brittleness. We utilize recent advances in interpretability to find the extent to which features such as coherence, content, vocabulary, and relevance are important for automated scoring mechanisms. We use this to investigate the oversensitivity i.e., large change in output score with a little change in input essay content) and overstability i.e., little change in output scores with large changes in input essay content) of AES. Our results indicate that autoscoring models, despite getting trained as "end-to-end" models with rich contextual embeddings such as BERT, behave like bag-of-words models. A few words determine the essay score without the requirement of any context making the model largely overstable. This is in stark contrast to recent probing studies on pre-trained representation learning models, which show that rich linguistic features such as parts-of-speech and morphology are encoded by them. Further, we also find that the models have learnt dataset biases, making them oversensitive. To deal with these issues, we propose detection-based protection models that can detect oversensitivity and overstability causing samples with high accuracies. We find that our proposed models are able to detect unusual attribution patterns and flag adversarial samples successfully.

Comprehensive evaluations of language models (LM) during both development and deployment phases are necessary because these models possess numerous capabilities (e.g., mathematical reasoning, legal support, or medical diagnostic) as well as safety risks (e.g., racial bias, toxicity, or misinformation). The average score across a wide range of benchmarks provides a signal that helps guide the use of these LMs in practice. Currently, holistic evaluations are costly due to the large volume of benchmark questions, making frequent evaluations impractical. A popular attempt to lower the cost is to compute the average score on a subset of the benchmark. This approach, unfortunately, often renders an unreliable measure of LM performance because the average score is often confounded with the difficulty of the questions in the benchmark subset. Item response theory (IRT) was designed to address this challenge, providing a reliable measurement by careful controlling for question difficulty. Unfortunately, question difficulty is expensive to estimate. Facing this challenge, we train a model that predicts question difficulty from its content, enabling a reliable measurement at a fraction of the cost. In addition, we leverage this difficulty predictor to further improve the evaluation efficiency through training a question generator given a difficulty level. This question generator is essential in adaptive testing, where, instead of using a random subset of the benchmark questions, informative questions are adaptively chosen based on the current estimation of LLM performance. Experiments on 22 common natural language benchmarks and 172 LMs show that this approach is more reliable and efficient compared to current common practice.

In this paper, we present a novel approach for segmenting pediatric brain tumors using a deep learning architecture, inspired by expert radiologists' segmentation strategies. Our model delineates four distinct tumor labels and is benchmarked on a held-out PED BraTS 2024 test set (i.e., pediatric brain tumor datasets introduced by BraTS). Furthermore, we evaluate our model's performance against the state-of-the-art (SOTA) model using a new external dataset of 30 patients from CBTN (Children's Brain Tumor Network), labeled in accordance with the PED BraTS 2024 guidelines and 2023 BraTS Adult Glioma dataset. We compare segmentation outcomes with the winning algorithm from the PED BraTS 2023 challenge as the SOTA model. Our proposed algorithm achieved an average Dice score of 0.642 and an HD95 of 73.0 mm on the CBTN test data, outperforming the SOTA model, which achieved a Dice score of 0.626 and an HD95 of 84.0 mm. Moreover, our model exhibits strong generalizability, attaining a 0.877 Dice score in whole tumor segmentation on the BraTS 2023 Adult Glioma dataset, surpassing existing SOTA. Our results indicate that the proposed model is a step towards providing more accurate segmentation for pediatric brain tumors, which is essential for evaluating therapy response and monitoring patient progress. Our source code is available at https://github.com/NUBagciLab/Pediatric-Brain-Tumor-Segmentation-Model.

Many students lack access to expert research mentorship. We ask whether an AI mentor can move undergraduates from an idea to a paper. We build METIS, a tool-augmented, stage-aware assistant with literature search, curated guidelines, methodology checks, and memory. We evaluate METIS against GPT-5 and Claude Sonnet 4.5 across six writing stages using LLM-as-a-judge pairwise preferences, student-persona rubrics, short multi-turn tutoring, and evidence/compliance checks. On 90 single-turn prompts, LLM judges preferred METIS to Claude Sonnet 4.5 in 71% and to GPT-5 in 54%. Student scores (clarity/actionability/constraint-fit; 90 prompts x 3 judges) are higher across stages. In multi-turn sessions (five scenarios/agent), METIS yields slightly higher final quality than GPT-5. Gains concentrate in document-grounded stages (D-F), consistent with stage-aware routing and groundings failure modes include premature tool routing, shallow grounding, and occasional stage misclassification.

As language models shift from single-shot answer generation toward multi-step reasoning that retrieves and consumes evidence mid-inference, evaluating the role of individual retrieved items becomes more important. Existing RAG evaluation typically targets final-answer quality, citation faithfulness, or answer-level attribution, but none of these directly targets the intervention-based, per-evidence-item utility view we study here. We introduce CUE-R, a lightweight intervention-based framework for measuring per-evidence-item operational utility in single-shot RAG using shallow observable retrieval-use traces. CUE-R perturbs individual evidence items via REMOVE, REPLACE, and DUPLICATE operators, then measures changes along three utility axes (correctness, proxy-based grounding faithfulness, and confidence error) plus a trace-divergence signal. We also outline an operational evidence-role taxonomy for interpreting intervention outcomes. Experiments on HotpotQA and 2WikiMultihopQA with Qwen-3 8B and GPT-5.2 reveal a consistent pattern: REMOVE and REPLACE substantially harm correctness and grounding while producing large trace shifts, whereas DUPLICATE is often answer-redundant yet not fully behaviorally neutral. A zero-retrieval control confirms that these effects arise from degradation of meaningful retrieval. A two-support ablation further shows that multi-hop evidence items can interact non-additively: removing both supports harms performance far more than either single removal. Our results suggest that answer-only evaluation misses important evidence effects and that intervention-based utility analysis is a practical complement for RAG evaluation.

Intelligent drug recommendation based on Electronic Health Records (EHRs) is critical for improving the quality and efficiency of clinical decision-making. By leveraging large-scale patient data, drug recommendation systems can assist physicians in selecting the most appropriate medications according to a patient's medical history, diagnoses, laboratory results, and comorbidities. Recent advances in large language models (LLMs) have shown remarkable capabilities in complex reasoning and medical text understanding, making them promising tools for drug recommendation tasks. However, the application of LLMs for Chinese clinical medication recommendation remains largely unexplored. In this work, we conduct a systematic investigation of LLM-based methodologies for Chinese discharge medication recommendation. We evaluate several representative LLM families (GLM, Llama, Qwen) under a unified methodological framework including zero-shot prompting, in-context learning, chain-of-thought prompting, and supervised fine-tuning using LoRA. We analyze model behavior across reasoning styles, error patterns, domain adaptation mechanisms, and robustness. Experimental results show that while supervised fine-tuning improves model performance, there remains substantial room for improvement, with the best model achieving the F1 score of 0.5648 and Jaccard score of 0.4477. Our findings highlight both the potential and limitations of LLMs for Chinese drug recommendation.

Speech deepfake detectors usually emit one score per utterance, but a borderline score does not reveal why two examples differ during retrospective error analysis. We ask whether a final score can be calibrated from component fields while keeping those fields visible for inspection. We build a decision record with a passive detector score and a score from a probe applied to a marked copy. It also includes retrieval support held out of the evaluated family, a margin from a support-set profile, and raw neighbor closeness. A cross-fit calibrator combines these fields and two differences between raw scores into one final score. On matched ASVspoof development data, the calibrated record reduces equal error rate (EER) by 3.48 percentage points relative to the fixed retrieval-augmented rule. It reaches 8.43% EER, whereas a passive WavLM baseline reaches 6.71% on the same subset. The record is therefore not the strongest detector in this comparison. Its value is to retain inspectable component fields while producing one scalar score for retrospective diagnosis.

This study explores the relationship between textual features and Information Engagement (IE) on digital platforms. It highlights the impact of computational linguistics and analytics on user interaction. The READ model is introduced to quantify key predictors like representativeness, ease of use, affect, and distribution, which forecast engagement levels. The model's effectiveness is validated through AB testing and randomized trials, showing strong predictive performance in participation (accuracy: 0.94), perception (accuracy: 0.85), perseverance (accuracy: 0.81), and overall IE (accuracy: 0.97). While participation metrics are strong, perception and perseverance show slightly lower recall and F1-scores, indicating some challenges. The study demonstrates that modifying text based on the READ model's insights leads to significant improvements. For example, increasing representativeness and positive affect boosts selection rates by 11 percent, raises evaluation averages from 3.98 to 4.46, and improves retention rates by 11 percent. These findings highlight the importance of linguistic factors in IE, providing a framework for enhancing digital text engagement. The research offers practical strategies applicable to fields like education, health, and media.

Experimental studies of generative AI in education mostly report average effects, yet field evidence shows that AI can narrow attainment gaps or widen them. We argue that the direction depends on the judgement burden, the expertise a learner must supply to screen AI output before learning from it, and that expert verification before release moves this burden from students to an accountable tutor. We test the argument in a two-cohort difference-in-differences design in which one half of a compulsory firstyear university economics course received AI-generated podcasts, FAQs and quiz-based study guides, produced with a source-grounded model and checked by a named graduate teaching assistant (170 students; 340 examination marks). Access was associated with a 2.34-mark advantage on a 50-mark component. The share of marks below the upper-second classification boundary fell by 24.7 percentage points relative to the counterfactual, effects were significant at every threshold from 23 to 31 marks and at none above, and roughly three-quarters of the average originated in the bottom quintile. The threshold estimate is robust to removing the lowest-scoring students from the pre-intervention cohort; the average effect is not. Interviews and feedback from 36 students indicate that the verification label gave students a reason to engage with AI-generated material without ending their scrutiny of it. Evaluations of AI learning resources that report only mean effects cannot detect whether the students the resources are meant to help are the ones who gain.

Training data influence estimation methods quantify the contribution of training documents to a model's output, making them a promising source of information for example-based explanations. As humans cannot interpret thousands of documents, only a small subset of the training data can be presented as an explanation. Although the choice of which documents to include directly affects explanation quality, previous evaluations of such systems have largely ignored any selection strategies. To address this, we propose a novel selection relevance score, a retraining-free metric that quantifies how useful a set of examples is for explaining a model's output. We validate this score through fine-tuning experiments, confirming that it can predict whether a set of examples supports or undermines the model's predictions. Using this metric, we further show that common selection strategies often underperform random selection. Motivated by this finding, we propose a strategy that balances influence and representativeness, enabling better use of selection budgets than naively selecting the highest-ranking examples.

This study presents a hybrid framework for predicting movie success. The framework integrates multi-task learning (MTL), GPT-based sentiment analysis, and Susceptible-Infected-Recovered (SIR) propagation modeling. The study examines limitations in existing approaches. It models static production attributes, information dissemination, and audience sentiment at the same time. The framework uses 5,840 films from 2004 to 2024 and approximate 300,000 user reviews. It shows predictive performance with classification accuracy of 0.964 and regression metrics of MAE 0.388. Ablation analysis indicates component interactions. Selective feature combinations perform better than the comprehensive model. This result questions assumptions about feature integration. The model shows virality patterns between successful and unsuccessful films. Innovations include epidemiological modeling for information diffusion, multidimensional sentiment features from GPT-based analysis, and a shared representation architecture that optimizes multiple success metrics. The framework provides applications in the film production lifecycle. It also contributes to understanding how audience engagement leads to commercial outcomes.

The technique of data augmentation (DA) is often used in machine learning for regularization purposes to better generalize under i.i.d. settings. In this work, we present a unifying framework with topics in causal inference to make a case for the use of DA beyond just the i.i.d. setting, but for generalization across interventions as well. Specifically, we argue that when the outcome generating mechanism is invariant to our choice of DA, then such augmentations can effectively be thought of as interventions on the treatment generating mechanism itself. This can potentially help to reduce bias in causal effect estimation arising from hidden confounders. In the presence of such unobserved confounding we typically make use of instrumental variables (IVs) -- sources of treatment randomization that are conditionally independent of the outcome. However, IVs may not be as readily available as DA for many applications, which is the main motivation behind this work. By appropriately regularizing IV based estimators, we introduce the concept of IV-like (IVL) regression for mitigating confounding bias and improving predictive performance across interventions even when certain IV properties are relaxed. Finally, we cast parameterized DA as an IVL regression problem and show that when used in composition can simulate a worst-case application of such DA, further improving performance on causal estimation and generalization tasks beyond what simple DA may offer. This is shown both theoretically for the population case and via simulation experiments for the finite sample case using a simple linear example. We also present real data experiments to support our case.

The ambition of the 2025 PNPL competition (Landau et al., 2025) was to launch a multi-year curriculum for non-invasive speech decoding. Designed to progress from foundational tasks toward the linguistic complexity required for a practical brain-computer interface (BCI), it set the stage with speech detection and phoneme classification tasks. Winning submissions reached F1-macro scores of 95.6% and 73.6% on the respective tasks (Elvers et al., 2026), highly significant advances. This success was built on the LibriBrain dataset (Özdogan et al., 2025), the largest within-subject MEG dataset recorded at the time with {sim}50 hours of data for one subject. However, while within-subject scale drives strong decoding performance, a practical BCI must generalise to new users from minutes of data, not hours. The 2026 PNPL competition responds to this challenge with LibriBrain100 (Mantegna et al., 2026), an extended LibriBrain dataset with 32 additional subjects ({sim}40 minutes each) plus even more within-subject data ({sim}80 hours). Advancing the curriculum of tasks to focus on word classification, two complementary tracks are presented in this competition: the Deep track targets within-subject word classification at scale, aiming at the best possible performance; the Broad track targets cross-subject generalisation, progressively reducing the amount of subject-specific fine-tuning data from {sim}40 to {sim}20 to {sim}10 minutes, a duration that falls within a clinically feasible range and brings us a step closer to a non-invasive BCI capable of restoring communication to people living with profound paralysis.

Accurate estimation of brain infarction (i.e., irreversibly damaged tissue) is critical for guiding treatment decisions in acute ischemic stroke. Reliable infarct prediction informs key clinical interventions, including the need for patient transfer to comprehensive stroke centers, the potential benefit of additional reperfusion attempts during mechanical thrombectomy, decisions regarding secondary neuroprotective treatments, and ultimately, prognosis of clinical outcomes. This work introduces the Ischemic Stroke Lesion Segmentation (ISLES) 2024 challenge, which focuses on the prediction of final infarct volumes from pre-interventional acute stroke imaging and clinical data. ISLES24 provides a comprehensive, multimodal setting where participants can leverage all clinically and practically available data, including full acute CT imaging, sub-acute follow-up MRI, and structured clinical information, across a train set of 150 cases. On the hidden test set of 98 cases, the top-performing model, a multimodal nnU-Net-based architecture, achieved a Dice score of 0.285 (+/- 0.213) and an absolute volume difference of 21.2 (+/- 37.2) mL, underlining the significant challenges posed by this task and the need for further advances in multimodal learning. This work makes two primary contributions: first, we establish a standardized, clinically realistic benchmark for post-treatment infarct prediction, enabling systematic evaluation of multimodal algorithmic strategies on a longitudinal stroke dataset; second, we analyze current methodological limitations and outline key research directions to guide the development of next-generation infarct prediction models.

Physicians now pose millions of clinical questions to AI tools each week, yet these tools are evaluated largely on hypothetical or exam-style questions, not those actually asked in practice. We report a blinded evaluation built on 620 Real-world Point-Of-Care Queries (Real-POCQi) submitted to the OpenEvidence (OE) platform by physicians spanning 30 specialties, as well as 187 questions from HealthBench. 149 practicing physicians across 36 states made head-to-head comparisons between answers from three frontier general-purpose models (Claude Opus 4.8, Gemini 3.1 Pro, and GPT-5.5) and a specialized clinical tool (OE), with graders matched to each question's specialty. When comparing answers along five dimensions relevant to clinical decision support -- accuracy, clinical utility, source quality, verifiability, & completeness -- physicians scored the specialized tool highest on all axes; in the primary analysis on Real-POCQi, win differences (margins between win and loss rates) ranged from 25 to 39 percentage points (p<0.001). Results remained consistent in sensitivity analyses stratifying by citation display, answer length, OE-user status, and Real-POCQi versus HealthBench. In parallel, LLM judges were found to systematically differ from expert judges, though both generally agreed on the best model. These findings underscore two conclusions: (i) AI tool evaluations should reflect real-world query distributions and use expert judges that mirror the specialization defining modern medicine and (ii) the consistent advantage of the specialized tool over general-purpose models does not necessarily mean that the latter cannot serve similar purposes, but that targeted engineering and customization can yield meaningful gains in performance for its users. We release Real-POCQi as a public benchmark, as well as the prespecified statistical analysis for reproducing results of this study.

HakemBench is a Turkish benchmark of typed decisions, in which the model under test reads a text, a question and a fixed set of options and returns a probability for every option. Version 1.0 is released fully open under CC BY 4.0, with 2,346 items and 4,275 choice, yes/no and score questions in seven tracks (fact-check triage, education, guardrails, legal routing, moderation, spam and phishing, and customer support). One harness scores decision quality (macro F1), calibration (from the normalised Brier score) and selective automation (from the normalised area under the generalised risk-coverage curve), combines them by a geometric mean and reports intervals from 2,000 bootstrap draws; probes for option order, paraphrase, English translation and substituted names are reported alongside. Most gold labels come from blind passes of one AI model family compared with the votes of a panel of large language models from other model families; they are not human-verified. On a board of 16 rows the leader scores a composite of 0.888 and the lab's own model is 7th at 0.660. Its numbers are not blind. Earlier runs' test results shaped its training data, so its guardrail, moderation and customer support numbers are flagged; with every model scored on the other four tracks only, its composite is 0.678, 6th of 16.

ARC-AGI-3 evaluates agents in interactive environments whose rules and objectives must be inferred from observation. We present Kepler, an open-source harness that represents hypotheses as executable world models and validates them through retrospective transition checks and conditional prediction checks. Under one frozen Claude Opus 5 configuration, Kepler obtained a server-verified 100.00 RHAE on all 25 public games, with no per-game model selection or score-conditioned reruns. On 181 of 183 completed levels, the final Opus attempt used no more actions than the corresponding median-human baseline. The retained board runs used 8,256 environment actions, of which 7,292 occurred in scored levels. Retained local provider-session records yield 858.0 million tokens, 97.37% cache reads, and a \$777.72 cost at September 1, 2026 API list-equivalent rates. We also report three evaluation failures: source-code leakage that produced an invalid perfect run, agents reconstructing a removed harness in a control condition, and autonomous repair masking a broken planner. A single-game observation case study showed that animation frames contained task-relevant information absent from settled text grids. Across the final Claude Opus 5 and GPT-5.6 Sol boards, 48 of 50 game-model cells reached 100. These results indicate that public-set score alone has limited discriminative value and motivate first-attempt, cost-conditioned, and verification-aware reporting.

Text classification is a fundamental language task in Natural Language Processing. A variety of sequential models is capable making good predictions yet there is lack of connection between language semantics and prediction results. This paper proposes a novel influence score (I-score), a greedy search algorithm called Backward Dropping Algorithm (BDA), and a novel feature engineering technique called the "dagger technique". First, the paper proposes a novel influence score (I-score) to detect and search for the important language semantics in text document that are useful for making good prediction in text classification tasks. Next, a greedy search algorithm called the Backward Dropping Algorithm is proposed to handle long-term dependencies in the dataset. Moreover, the paper proposes a novel engineering technique called the "dagger technique" that fully preserve the relationship between explanatory variable and response variable. The proposed techniques can be further generalized into any feed-forward Artificial Neural Networks (ANNs) and Convolutional Neural Networks (CNNs), and any neural network. A real-world application on the Internet Movie Database (IMDB) is used and the proposed methods are applied to improve prediction performance with an 81% error reduction comparing with other popular peers if I-score and "dagger technique" are not implemented.

We developed an explainable artificial intelligence (AI) early warning score (xAI-EWS) system for early detection of acute critical illness. While maintaining a high predictive performance, our system explains to the clinician on which relevant electronic health records (EHRs) data the prediction is grounded. Acute critical illness is often preceded by deterioration of routinely measured clinical parameters, e.g., blood pressure and heart rate. Early clinical prediction is typically based on manually calculated screening metrics that simply weigh these parameters, such as Early Warning Scores (EWS). The predictive performance of EWSs yields a tradeoff between sensitivity and specificity that can lead to negative outcomes for the patient. Previous work on EHR-trained AI systems offers promising results with high levels of predictive performance in relation to the early, real-time prediction of acute critical illness. However, without insight into the complex decisions by such system, clinical translation is hindered. In this letter, we present our xAI-EWS system, which potentiates clinical translation by accompanying a prediction with information on the EHR data explaining it.

Estimating the causal effects of interventions is crucial to policy and decision-making, yet outcome data are often missing or subject to non-standard measurement error. While ground-truth outcomes can sometimes be obtained through costly data annotation or follow-up, budget constraints typically allow only a fraction of the dataset to be labeled. We address this challenge by optimizing which data points should be sampled for outcome information in order to improve efficiency in average treatment effect estimation with missing outcomes. We derive a closed-form solution for the optimal batch sampling probability by minimizing the asymptotic variance of a doubly robust estimator for causal inference with missing outcomes. Motivated by our street outreach partners, we extend the framework to costly annotations of unstructured data, such as text or images in healthcare and social services. Across simulated and real-world datasets, including one of outreach interventions in homelessness services, our approach achieves substantially lower mean-squared error and recovers the AIPW estimate with fewer labels than existing baselines. In practice, we show that our method can match confidence intervals obtained with 361 random samples using only 90 optimized samples - saving 75% of the labeling budget.

Large language models (LLMs), renowned for their powerful conversational abilities, are widely recognized as exceptional tools in the field of education, particularly in the context of automated intelligent instruction systems for language learning. In this paper, we propose a scoring system based on LLMs, motivated by their positive impact on text-related scoring tasks. Specifically, the speech encoder first maps the learner's speech into contextual features. The adapter layer then transforms these features to align with the text embedding in latent space. The assessment task-specific prefix and prompt text are embedded and concatenated with the features generated by the modality adapter layer, enabling the LLMs to predict accuracy and fluency scores. Our experiments demonstrate that the proposed scoring systems achieve competitive results compared to the baselines on the Speechocean762 datasets. Moreover, we also conducted an ablation study to better understand the contributions of the prompt text and training strategy in the proposed scoring system.

Probes are the workhorse of interpretability. If a model's hidden states predict a variable, the model is said to represent it. But a probe score has no fixed meaning. An R^2 of 0.6 may only reflect what the input already gives away, and the same score can mean different things on different data. We propose reading every probe score against two reference points: a floor, what a declared set of simple inputs already predicts, and a ceiling, what the full input can predict. The gap between them, the headroom, is the range in which a probe can show that a model computes something beyond the simple inputs. We prove that headroom vanishes in two ways: the target stops depending on a hidden variable the model must infer, or the input stops revealing it. We test this on transformers trained for in-context meta-analysis, which must infer the hidden heterogeneity between studies to weight them correctly, and where both reference points are known. Under distribution shift, probe scores fall and prediction error rises 12--15times, yet the model recovers a similar share of the headroom, indicating that the data lost information, not the representation. We then analyze the real models. The single-cell foundation model scGPT encodes biological variability only partially. We also revisit four influential LLM probing studies, which claim that models represent geography, the state of an Othello board, truth, and the demographics of their users. Against a floor computed from the input text alone, some of these claims hold, while others are largely explained by the text itself.

The integration of large language models (LLMs) into medical practice holds transformative potential, yet their real-world clinical utility remains limited by critical alignment challenges: (1) a disconnect between static evaluation benchmarks and dynamic clinical cognitive needs, (2) difficulties in adapting to evolving, multi-source medical standards, and (3) the inability of conventional reward models to capture nuanced, multi-dimensional medical quality criteria. To address these gaps, we propose MR-RML (Multidimensional Rubric-oriented Reward Model Learning) via GPRC (Geometric Projection Reference Constraints), a novel alignment framework that integrates medical standards into a structured "Dimensions-Scenarios-Disciplines" matrix to guide data generation and model optimization. MR-RML introduces three core innovations: (1) a "Dimensions-Scenarios-Disciplines" medical standard system that embeds domain standards into the full training pipeline; (2) an independent multi-dimensional reward model that decomposes evaluation criteria, shifting from real-time rubric-based scoring to internalized reward modeling for improved consistency and cost-efficiency; (3) geometric projection reference constraints that transform medical cognitive logic into mathematical regularization, aligning scoring gradients with clinical reasoning and enabling synthetic data-driven training. Through extensive evaluations on the authoritative medical benchmark Healthbench, our method yields substantial performance gains over the base LLM Qwen-32B (45% on the full subset and 85% on Hard subset, respectively). It achieves a SOTA among open-source LLMs with scores of 62.7 (full subset) and 44.7 (hard subset), while also outperforming the majority of closed-source models.

Mental health disorders affect a substantial proportion of the global population, yet a persistent shortage of trained practitioners leaves the majority without adequate care. Large language model (LLM)-based counselors present a promising direction for delivering scalable conversational psychological support. Offline model training alone leaves limited room to adapt to individual clients or to learn from ongoing therapeutic interaction at test time. We introduce PsyEvo, an LLM-based counseling framework that enables both client-specific personalization and response-policy improvement at test time through three components: Hierarchical Bayesian Skill Policy (HBSP) personalizes what intervention to apply by maintaining a per-client skill posterior updated from session feedback; Inter-session Listwise Preference Optimization (LiPO) improves how the selected skill is expressed by updating a shared response adapter from cross-client preference evidence; and State-conditioned Ordinal Credit Assignment (SOCA) supplies candidate preferences and trajectory credit to the two components through consistency-checked comparisons and ordinal projection. In simulated-client evaluation with shared online cohort adaptation, PsyEvo obtains 7.684 Overall on PsychEval and exceeds every component variant in each of three matched runs. Removing individual components lowers mean overall score by 0.138--0.171 under the shared configuration, supporting conditional contributions within the complete scaffold. Our code is available at https://github.com/Lingxi-mental-health/PsyEvo

This study investigates the consistency of feedback ratings generated by OpenAI's GPT-4, a state-of-the-art artificial intelligence language model, across multiple iterations, time spans and stylistic variations. The model rated responses to tasks within the Higher Education (HE) subject domain of macroeconomics in terms of their content and style. Statistical analysis was conducted in order to learn more about the interrater reliability, consistency of the ratings across iterations and the correlation between ratings in terms of content and style. The results revealed a high interrater reliability with ICC scores ranging between 0.94 and 0.99 for different timespans, suggesting that GPT-4 is capable of generating consistent ratings across repetitions with a clear prompt. Style and content ratings show a high correlation of 0.87. When applying a non-adequate style the average content ratings remained constant, while style ratings decreased, which indicates that the large language model (LLM) effectively distinguishes between these two criteria during evaluation. The prompt used in this study is furthermore presented and explained. Further research is necessary to assess the robustness and reliability of AI models in various use cases.

This study investigates GPT-4's assessment of its performance in healthcare applications. A simple prompting technique was used to prompt the LLM with questions taken from the United States Medical Licensing Examination (USMLE) questionnaire and it was tasked to evaluate its confidence score before posing the question and after asking the question. The questionnaire was categorized into two groups-questions with feedback (WF) and questions with no feedback(NF) post-question. The model was asked to provide absolute and relative confidence scores before and after each question. The experimental findings were analyzed using statistical tools to study the variability of confidence in WF and NF groups. Additionally, a sequential analysis was conducted to observe the performance variation for the WF and NF groups. Results indicate that feedback influences relative confidence but doesn't consistently increase or decrease it. Understanding the performance of LLM is paramount in exploring its utility in sensitive areas like healthcare. This study contributes to the ongoing discourse on the reliability of AI, particularly of LLMs like GPT-4, within healthcare, offering insights into how feedback mechanisms might be optimized to enhance AI-assisted medical education and decision support.

Discovering causal structures from data is a challenging inference problem of fundamental importance in all areas of science. The appealing properties of neural networks have recently led to a surge of interest in differentiable neural network-based methods for learning causal structures from data. So far, differentiable causal discovery has focused on static datasets of observational or fixed interventional origin. In this work, we introduce an active intervention targeting (AIT) method which enables a quick identification of the underlying causal structure of the data-generating process. Our method significantly reduces the required number of interactions compared with random intervention targeting and is applicable for both discrete and continuous optimization formulations of learning the underlying directed acyclic graph (DAG) from data. We examine the proposed method across multiple frameworks in a wide range of settings and demonstrate superior performance on multiple benchmarks from simulated to real-world data.

Accelerating MRI scans is one of the principal outstanding problems in the MRI research community. Towards this goal, we hosted the second fastMRI competition targeted towards reconstructing MR images with subsampled k-space data. We provided participants with data from 7,299 clinical brain scans (de-identified via a HIPAA-compliant procedure by NYU Langone Health), holding back the fully-sampled data from 894 of these scans for challenge evaluation purposes. In contrast to the 2019 challenge, we focused our radiologist evaluations on pathological assessment in brain images. We also debuted a new Transfer track that required participants to submit models evaluated on MRI scanners from outside the training set. We received 19 submissions from eight different groups. Results showed one team scoring best in both SSIM scores and qualitative radiologist evaluations. We also performed analysis on alternative metrics to mitigate the effects of background noise and collected feedback from the participants to inform future challenges. Lastly, we identify common failure modes across the submissions, highlighting areas of need for future research in the MRI reconstruction community.

Recent advances in psychotherapy have focused on treatment personalization, such as by selecting treatment modules based on personalized networks. However, estimating personalized networks typically requires intensive longitudinal data, which is not always feasible. A solution to facilitate scalability of network-driven treatment personalization is leveraging LLMs. In this study, we present an end-to-end pipeline for automatically generating client networks from 77 therapy transcripts to support case conceptualization and treatment planning. We annotated 3364 psychological processes and their corresponding dimensions in therapy transcripts. Using these data, we applied in-context learning to jointly identify psychological processes and their dimensions. The method achieved high performance even with a few training examples. To organize the processes into networks, we introduced a two-step method that grouped them into clinically meaningful clusters. We then generated explanation-augmented relationships between clusters. Experts found that networks produced by our multi-step approach outperformed those built with direct prompting for clinical utility and interpretability, with up to 90% preferring our approach. In addition, the networks were rated favorably by experts, with scores for clinical relevance, novelty, and usefulness ranging from 72-75%. Our findings provide a proof of concept for using LLMs to create clinically relevant networks from therapy transcripts. Advantages of our approach include bottom-up case conceptualization from client utterances in therapy sessions and identification of latent themes. Networks generated from our pipeline may be used in clinical settings and supervision and training. Future research should examine whether these networks improve treatment outcomes relative to other methods of treatment personalization, including statistically estimated networks.

The evaluation of Large Language Models (LLMs) in healthcare has been dominated by physician-centric, English-language benchmarks, creating a dangerous illusion of competence that ignores the interprofessional nature of patient care. To provide a more holistic and realistic assessment, we introduce HealthQA-BR, the first large-scale, system-wide benchmark for Portuguese-speaking healthcare. Comprising 5,632 questions from Brazil's national licensing and residency exams, it uniquely assesses knowledge not only in medicine and its specialties but also in nursing, dentistry, psychology, social work, and other allied health professions. We conducted a rigorous zero-shot evaluation of over 20 leading LLMs. Our results reveal that while state-of-the-art models like GPT 4.1 achieve high overall accuracy (86.6%), this top-line score masks alarming, previously unmeasured deficiencies. A granular analysis shows performance plummets from near-perfect in specialties like Ophthalmology (98.7%) to barely passing in Neurosurgery (60.0%) and, most notably, Social Work (68.4%). This "spiky" knowledge profile is a systemic issue observed across all models, demonstrating that high-level scores are insufficient for safety validation. By publicly releasing HealthQA-BR and our evaluation suite, we provide a crucial tool to move beyond single-score evaluations and toward a more honest, granular audit of AI readiness for the entire healthcare team.

Speech patterns have been identified as potential diagnostic markers for neuropsychiatric conditions. However, most studies only compare a single clinical group to healthy controls, whereas clinical practice often requires differentiating between multiple potential diagnoses (multiclass settings). To address this, we assembled a dataset of repeated recordings from 420 participants (67 with major depressive disorder, 106 with schizophrenia and 46 with autism, as well as matched controls), and tested the performance of a range of conventional machine learning models and advanced Transformer models on both binary and multiclass classification, based on voice and text features. While binary models performed comparably to previous research (F1 scores between 0.54-0.75 for autism spectrum disorder, ASD; 0.67-0.92 for major depressive disorder, MDD; and 0.71-0.83 for schizophrenia); when differentiating between multiple diagnostic groups performance decreased markedly (F1 scores between 0.35-0.44 for ASD, 0.57-0.75 for MDD, 0.15-0.66 for schizophrenia, and 0.38-0.52 macro F1). Combining voice and text-based models yielded increased performance, suggesting that they capture complementary diagnostic information. Our results indicate that models trained on binary classification may learn to rely on markers of generic differences between clinical and non-clinical populations, or markers of clinical features that overlap across conditions, rather than identifying markers specific to individual conditions. We provide recommendations for future research in the field, suggesting increased focus on developing larger transdiagnostic datasets that include more fine-grained clinical features, and that can support the development of models that better capture the complexity of neuropsychiatric conditions and naturalistic diagnostic assessment.

While large language models (LLMs) achieve near-perfect scores on medical licensing exams, these evaluations inadequately reflect the complexity and diversity of real-world clinical practice. We introduce MedHELM, an extensible evaluation framework for assessing LLM performance for medical tasks with three key contributions. First, a clinician-validated taxonomy spanning 5 categories, 22 subcategories, and 121 tasks developed with 29 clinicians. Second, a comprehensive benchmark suite comprising 35 benchmarks (17 existing, 18 newly formulated) providing complete coverage of all categories and subcategories in the taxonomy. Third, a systematic comparison of LLMs with improved evaluation methods (using an LLM-jury) and a cost-performance analysis. Evaluation of 9 frontier LLMs, using the 35 benchmarks, revealed significant performance variation. Advanced reasoning models (DeepSeek R1: 66% win-rate; o3-mini: 64% win-rate) demonstrated superior performance, though Claude 3.5 Sonnet achieved comparable results at 40% lower estimated computational cost. On a normalized accuracy scale (0-1), most models performed strongly in Clinical Note Generation (0.73-0.85) and Patient Communication & Education (0.78-0.83), moderately in Medical Research Assistance (0.65-0.75), and generally lower in Clinical Decision Support (0.56-0.72) and Administration & Workflow (0.53-0.63). Our LLM-jury evaluation method achieved good agreement with clinician ratings (ICC = 0.47), surpassing both average clinician-clinician agreement (ICC = 0.43) and automated baselines including ROUGE-L (0.36) and BERTScore-F1 (0.44). Claude 3.5 Sonnet achieved comparable performance to top models at lower estimated cost. These findings highlight the importance of real-world, task-specific evaluation for medical use of LLMs and provides an open source framework to enable this.

Representation engineering methods have recently shown promise for enabling efficient steering of model behavior. However, evaluation pipelines for these methods have primarily relied on subjective demonstrations, instead of quantitative, objective metrics. We aim to take a step towards addressing this issue by advocating for four properties missing from current evaluations: (i) contexts sufficiently similar to downstream tasks should be used for assessing intervention quality; (ii) model likelihoods should be accounted for; (iii) evaluations should allow for standardized comparisons across different target behaviors; and (iv) baseline comparisons should be offered. We introduce an evaluation pipeline grounded in these criteria, offering both a quantitative and visual analysis of how effectively a given method works. We use this pipeline to evaluate two representation engineering methods on how effectively they can steer behaviors such as truthfulness and corrigibility, finding that some interventions are less effective than previously reported.

Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation across various domains, including medicine. We present a comprehensive evaluation of GPT-4, a state-of-the-art LLM, on medical competency examinations and benchmark datasets. GPT-4 is a general-purpose model that is not specialized for medical problems through training or engineered to solve clinical tasks. Our analysis covers two sets of official practice materials for the USMLE, a three-step examination program used to assess clinical competency and grant licensure in the United States. We also evaluate performance on the MultiMedQA suite of benchmark datasets. Beyond measuring model performance, experiments were conducted to investigate the influence of test questions containing both text and images on model performance, probe for memorization of content during training, and study probability calibration, which is of critical importance in high-stakes applications like medicine. Our results show that GPT-4, without any specialized prompt crafting, exceeds the passing score on USMLE by over 20 points and outperforms earlier general-purpose models (GPT-3.5) as well as models specifically fine-tuned on medical knowledge (Med-PaLM, a prompt-tuned version of Flan-PaLM 540B). In addition, GPT-4 is significantly better calibrated than GPT-3.5, demonstrating a much-improved ability to predict the likelihood that its answers are correct. We also explore the behavior of the model qualitatively through a case study that shows the ability of GPT-4 to explain medical reasoning, personalize explanations to students, and interactively craft new counterfactual scenarios around a medical case. Implications of the findings are discussed for potential uses of GPT-4 in medical education, assessment, and clinical practice, with appropriate attention to challenges of accuracy and safety.

Large language models (LLMs) are increasingly used in clinical and care settings. This exploratory study investigates whether LLMs exhibit sycophantic behavior - adapting their responses to social expectation signals rather than maintaining professional quality - in the context of dementia care. Five prompts with systematically increasing confirmatory and authority-related framing (P1 neutral to P5 authority-signaled implementation support) were submitted to four LLMs (GPT-5, Claude Sonnet 4.6, Gemini 3.1 Pro, Mistral Large), each repeated five times (N = 100 responses). Responses were evaluated using an LLM-as-a-Judge methodology against seven nursing-ethical quality criteria (K1-K7) and a tone scale (0-3). All models showed significant negative Spearman correlations between prompt level and response quality (rho ranging from -0.543 to -0.734, all p < 0.01). Mistral Large exhibited the most pronounced effect (rho = -0.734), with mean scores dropping from 6.0/7 at P1 to 0.2/7 at P5. The findings suggest that LLMs pose context-sensitive risks in high-stakes care environments and that prompt framing significantly shapes response quality - a dimension that has received insufficient attention in healthcare AI deployment.

A benchmark score compares a system output against a reference, and methodological attention falls almost entirely on the first term. We measure the second. The retained annotation record of a six-language benchmark for personally identifiable information contains two independent annotator labellings, the aggregate shipped as gold, and a reviewer gold from independent expert re-annotation of a sample. Using it, we hold the scored output fixed and exchange the reference. The score moves by 4.95 F1 points for one output and 2.00 for the other (95% CIs [3.23, 6.27] and [0.26, 3.37]), and by 7.55 in the worst language. The comparison between two outputs moves as well: the paired interaction between reference and system is +2.95 points (CI [+1.97, +3.87]), survives correction for multiple testing, and changes one language's margin outright. The cause is an undocumented aggregation default that usually kept one annotator when adjudication did not fire, making the shipped reference a partial copy of an output being scored. We report the resulting reference-sensitivity band, show how to compute one from any retained annotation record, and argue that the quantity belongs beside the score.

In this work we design an end-to-end deep learning architecture for predicting, on Chest X-rays images (CXR), a multi-regional score conveying the degree of lung compromise in COVID-19 patients. Such semi-quantitative scoring system, namely Brixia~score, is applied in serial monitoring of such patients, showing significant prognostic value, in one of the hospitals that experienced one of the highest pandemic peaks in Italy. To solve such a challenging visual task, we adopt a weakly supervised learning strategy structured to handle different tasks (segmentation, spatial alignment, and score estimation) trained with a "from-the-part-to-the-whole" procedure involving different datasets. In particular, we exploit a clinical dataset of almost 5,000 CXR annotated images collected in the same hospital. Our BS-Net demonstrates self-attentive behavior and a high degree of accuracy in all processing stages. Through inter-rater agreement tests and a gold standard comparison, we show that our solution outperforms single human annotators in rating accuracy and consistency, thus supporting the possibility of using this tool in contexts of computer-assisted monitoring. Highly resolved (super-pixel level) explainability maps are also generated, with an original technique, to visually help the understanding of the network activity on the lung areas. We also consider other scores proposed in literature and provide a comparison with a recently proposed non-specific approach. We eventually test the performance robustness of our model on an assorted public COVID-19 dataset, for which we also provide Brixia~score annotations, observing good direct generalization and fine-tuning capabilities that highlight the portability of BS-Net in other clinical settings. The CXR dataset along with the source code and the trained model are publicly released for research purposes.

Recent incidents involving LLMs used for mental-health support reveal a critical evaluation gap: surface-level safety scores do not capture how models behave across realistic, emotionally sensitive interactions over time. Existing benchmarks measure knowledge, safety, or static response quality, but miss whether LLM interactions help users keep reflecting, coping, and making decisions themselves. We formalize this missing dimension as COGNITIVE ATROPHY, a process-level behavioural measure in AI-mediated mental-health support distinct from safety and helpfulness. To measure it, we introduce COGNITIVE ATROPHY BENCH, a clinically grounded benchmark built from 1,576 fully human-generated counseling conversations, 15,680 turns, and 42,230 responses from five LLMs. Three clinical and neuropsychology experts developed a 20-attribute schema spanning user context, response behaviour, and global risk flags; six trained clinical reviewers applied it with span-grounded evidence, producing 5,324 reviewer judgments. We further introduce the User-Input Risk Index (UIRI), the Cognitive Atrophy Risk Index (ARI), and trajectory summaries. Across five LLMs, models show a consistent moderate-to-high level of atrophy-aligned behaviour across single and multi-turn settings. While models generally respond to overt safety cues, they adapt less reliably when users seek solutions or decisions. The dominant recurring patterns are directive advice, problem-solving, recommendation responses, topic shifts, and forms of validation that may reinforce dependence rather than reflection. Our work makes COGNITIVE ATROPHY measurable and provides a foundation for auditing model behaviour in sensitive LLM conversations.

Large language model (LLM) agents increasingly take actions (screening applicants, recommending credit, triaging patients), yet fairness for LLMs is still measured by grading answers. We introduce AgentFairBench, a cheap, reproducible, multi-domain benchmark for demographic disparity in the actions of LLM agents. Grounded in a companion framework, the Bias Conduction Framework (BCF, restated here), it spans three regulator-anchored domains: hiring, lending, and medical triage. Synthetic, demographic-neutral profiles are evaluated in counterfactual matched sets that vary only a name-coded race x gender signal (in the Bertrand Mullainathan tradition), under four agent scaffolds of increasing agency (direct, chain-of-thought, multi-agent deliberation, tool-augmented). A NumPy-only harness computes counterfactual flip rate, mean absolute score difference (MASD), action-rate disparity, and tool-invocation disparity, with bootstrap confidence intervals, paired tests, and false-discovery-rate control, for single-digit dollars per model. A live leaderboard with a held-out private split and a contamination canary admits external models by submission. Our pilot (864 decisions plus a test-retest replication) carries a methodological lesson: comparing a six-group score spread against a two-run noise difference overstates disparity by ~ 2.4X through statistic arity alone. Against an arity matched noise floor and an omnibus group test, claude haiku 4 5 shows no demographic effect above sampling noise (0 of 120 pairwise and 0 of 9 omnibus contrasts survive correction); a planted-bias test confirms the instrument detects disparity when present. The contribution is a sound, sensitive, adoption-ready instrument, the arity matched null methodology, and open artifacts to scale it. Code, data, and harness are released under open licenses, with an anonymized review artifact.

Identifying effective interventions from the scientific literature is challenging due to the high volume of publications, specialized terminology, and inconsistent reporting formats, making manual curation laborious and prone to oversight. To address this challenge, this paper proposes a novel framework leveraging large language models (LLMs), which integrates a progressive ontology prompting (POP) algorithm with a dual-agent system, named LLM-Duo. On the one hand, the POP algorithm conducts a prioritized breadth-first search (BFS) across a predefined ontology, generating structured prompt templates and action sequences to guide the automatic annotation process. On the other hand, the LLM-Duo system features two specialized LLM agents, an explorer and an evaluator, working collaboratively and adversarially to continuously refine annotation quality. We showcase the real-world applicability of our framework through a case study focused on speech-language intervention discovery. Experimental results show that our approach surpasses advanced baselines, achieving more accurate and comprehensive annotations through a fully automated process. Our approach successfully identified 2,421 interventions from a corpus of 64,177 research articles in the speech-language pathology domain, culminating in the creation of a publicly accessible intervention knowledge base with great potential to benefit the speech-language pathology community.