Daily Papers

Safety alignment of large reasoning models (LRMs) via supervised fine-tuning (SFT) and reinforcement learning (RL) often yields near-perfect safety scores, yet this apparent success comes at the cost of severe over-refusal and degraded general capabilities. Through systematic empirical analysis, we find that these failures are closely associated with the learning of spurious shortcuts rather than robust intent-sensitive safety evaluation. Specifically, we identify two dominant shortcuts: formatting shortcuts, where refusal behaviors are overly bound to structural prompt templates that frequently appear in safety alignment corpora; and lexical shortcuts, where sensitive keywords reflexively trigger refusals on benign queries. To mitigate reliance on these shortcuts, we propose DeShortcut-Align, a shortcut-decoupling alignment framework that reduces dependence on superficial cues. DeShortcut-Align operates across three coordinated stages: (1) Refusal Sensitivity Attribution, which masks input tokens to quantify their impact on the final refusal response distribution; (2) Attribution-Guided Contrastive Augmentation, which constructs benign contrastive samples using high-sensitivity tokens to mitigate lexical shortcuts; and (3) Counterfactual Consistency Regularization, which constructs template-ablated states via attention blinding to enforce decision consistency across SFT and RL, mitigating formatting shortcut dependence. Experiments on 7B and 14B models demonstrate that DeShortcut-Align significantly improves robustness against template-stripping bypass attacks (reducing performance drops by up to 72%), substantially reduces over-refusal by over 58%, and better preserves general-purpose reasoning capabilities, thereby mitigating the alignment tax commonly observed in safety training.

Refusal behavior in large language models (LLMs) enables them to decline responding to harmful, unethical, or inappropriate prompts, ensuring alignment with ethical standards. This paper investigates refusal behavior across six LLMs from three architectural families. We challenge the assumption of refusal as a linear phenomenon by employing dimensionality reduction techniques, including PCA, t-SNE, and UMAP. Our results reveal that refusal mechanisms exhibit nonlinear, multidimensional characteristics that vary by model architecture and layer. These findings highlight the need for nonlinear interpretability to improve alignment research and inform safer AI deployment strategies.

Reliable Large Language Models (LLMs) should abstain when confidence is insufficient. However, prior studies often treat refusal as a generic "I don't know'', failing to distinguish input-level ambiguity (data uncertainty) from capability limitations (model uncertainty). This lack of distinction limits downstream action decisions like requesting clarification or invoking external tools. In this work, we introduce UA-Bench, a benchmark of over 3,500 questions drawn from six datasets spanning knowledge-intensive and reasoning-intensive tasks, designed to evaluate explicit uncertainty attribution. An evaluation of 18 frontier LLMs shows that even state-of-the-art models struggle to reliably discriminate between data uncertainty and model uncertainty, and that high answer accuracy does not necessarily imply strong uncertainty attribution ability. To narrow this gap, we propose a lightweight data synthesis and reinforcement learning strategy. Experiments on both Qwen3-4B-Instruct-2507 and Qwen3-8B in thinking mode show that the proposed method improves uncertainty attribution while preserving answer accuracy. Our code and data are publicly available now.

Large language models (LLMs) routinely face requests that should be refused, creating a trade-off between helpfulness and harm prevention. However, refusals themselves can be helpful. In high-risk interactions involving crisis, coercion, or escalating intent, blunt non-compliance may prevent direct harm while still failing to support the needs of the person behind the request. We present PsychoSafe, a psychologically-informed refusal framework that reframes refusal as structured supportive communication grounded in evidence-based intervention strategies. To develop PsychoSafe, we construct a corpus of 8019 prompt-response pairs spanning five psychologically salient risk domains and apply prompting and parameter-efficient fine-tuning to Qwen 3.5 27B. On a balanced validation set of 500 prompts, evaluated with an LLM judge and validated through human ratings, PsychoSafe prompting improves overall refusal quality by 28.1% over a generic baseline, with particularly strong gains in external resource referral (+46.8%) and psychological grounding (+34.8%), while preserving downstream performance on non-refusal tasks. Fine-tuning achieves near-perfect refusal and resource-referral rates but reduces response relevance. Additional evaluations on SORRY-Bench and XSTest show strong in-domain robustness but limited out-of-domain generalization, suggesting that future work should diversify fine-tuning data to help models apply interventions selectively rather than schematically.

A key component of building safe and reliable language models is enabling the models to appropriately refuse to follow certain instructions or answer certain questions. We may want models to output refusal messages for various categories of user queries, for example, ill-posed questions, instructions for committing illegal acts, or queries which require information past the model's knowledge horizon. Engineering models that refuse to answer such questions is complicated by the fact that an individual may want their model to exhibit varying levels of sensitivity for refusing queries of various categories, and different users may want different refusal rates. The current default approach involves training multiple models with varying proportions of refusal messages from each category to achieve the desired refusal rates, which is computationally expensive and may require training a new model to accommodate each user's desired preference over refusal rates. To address these challenges, we propose refusal tokens, one such token for each refusal category or a single refusal token, which are prepended to the model's responses during training. We then show how to increase or decrease the probability of generating the refusal token for each category during inference to steer the model's refusal behavior. Refusal tokens enable controlling a single model's refusal rates without the need of any further fine-tuning, but only by selectively intervening during generation.

Refusal is a key safety behavior in aligned language models, yet the internal mechanisms driving refusals remain opaque. In this work, we conduct a mechanistic study of refusal in instruction-tuned LLMs using sparse autoencoders to identify latent features that causally mediate refusal behaviors. We apply our method to two open-source chat models and intervene on refusal-related features to assess their influence on generation, validating their behavioral impact across multiple harmful datasets. This enables a fine-grained inspection of how refusal manifests at the activation level and addresses key research questions such as investigating upstream-downstream latent relationship and understanding the mechanisms of adversarial jailbreaking techniques. We also establish the usefulness of refusal features in enhancing generalization for linear probes to out-of-distribution adversarial samples in classification tasks. We open source our code in https://github.com/wj210/refusal_sae.

Large reasoning models (LRMs) with multi-step reasoning capabilities have shown remarkable problem-solving abilities, yet they exhibit concerning safety vulnerabilities that remain poorly understood. In this work, we investigate why safety alignment fails in reasoning models through a mechanistic interpretability lens. Using a linear probing approach to trace refusal intentions across token positions, we discover a striking phenomenon termed as refusal cliff: many poorly-aligned reasoning models correctly identify harmful prompts and maintain strong refusal intentions during their thinking process, but experience a sharp drop in refusal scores at the final tokens before output generation. This suggests that these models are not inherently unsafe; rather, their refusal intentions are systematically suppressed. Through causal intervention analysis, we identify a sparse set of attention heads that negatively contribute to refusal behavior. Ablating just 3\% of these heads can reduce attack success rates below 10\%. Building on these mechanistic insights, we propose Cliff-as-a-Judge, a novel data selection method that identifies training examples exhibiting the largest refusal cliff to efficiently repair reasoning models' safety alignment. This approach achieves comparable safety improvements using only 1.7\% of the vanilla safety training data, demonstrating a less-is-more effect in safety alignment.

Safety-aligned language models systematically refuse harmful requests. While activation steering can modulate refusal, ablating the raw "refusal vector" calculated from contrastive harmful and harmless prompts often causes collateral damage and distribution drift. We argue this degradation occurs because the raw vector is polysemantic, entangling the refusal signal with core capability circuits and linguistic style. We introduce Surgical Refusal Ablation (SRA) to distill these steering directions. SRA constructs a registry of independent Concept Atoms representing protected capabilities and stylistic confounds, then uses ridge-regularized spectral residualization to orthogonalize the refusal vector against these directions. This yields a clean refusal direction that targets refusal-relevant structure while minimizing disruption to the model's semantic geometry. Across five models (Qwen3-VL and Ministral series), SRA achieves deep refusal reduction (0-2%) with negligible perplexity impact on Wikitext-2 (mean delta PPL approx. 0.02) and minimal distribution drift. Notably, standard ablation on Qwen3-VL-4B induces severe drift (first-token KL = 2.088), whereas SRA maintains the original distribution (KL = 0.044) while achieving the same 0% refusal rate. Using teacher-forced perplexity on GSM8K and MBPP as a high-resolution capability proxy, we show SRA preserves math and code distributions. These results suggest that common "model damage" is often "Ghost Noise," defined as the spectral bleeding of the dirty refusal direction into capability subspaces.

Refusal refers to the functional behavior enabling safety-aligned language models to reject harmful or unethical prompts. Following the growing scientific interest in mechanistic interpretability, recent work encoded refusal behavior as a single direction in the model's latent space; e.g., computed as the difference between the centroids of harmful and harmless prompt representations. However, emerging evidence suggests that concepts in LLMs often appear to be encoded as a low-dimensional manifold embedded in the high-dimensional latent space. Motivated by these findings, we propose a novel method leveraging Self-Organizing Maps (SOMs) to extract multiple refusal directions. To this end, we first prove that SOMs generalize the prior work's difference-in-means technique. We then train SOMs on harmful prompt representations to identify multiple neurons. By subtracting the centroid of harmless representations from each neuron, we derive a set of multiple directions expressing the refusal concept. We validate our method on an extensive experimental setup, demonstrating that ablating multiple directions from models' internals outperforms not only the single-direction baseline but also specialized jailbreak algorithms, leading to an effective suppression of refusal. Finally, we conclude by analyzing the mechanistic implications of our approach.

Since the release of OpenAI's ChatGPT, generative language models have attracted extensive public attention. The increased usage has highlighted generative models' broad utility, but also revealed several forms of embedded bias. Some is induced by the pre-training corpus; but additional bias specific to generative models arises from the use of subjective fine-tuning to avoid generating harmful content. Fine-tuning bias may come from individual engineers and company policies, and affects which prompts the model chooses to refuse. In this experiment, we characterize ChatGPT's refusal behavior using a black-box attack. We first query ChatGPT with a variety of offensive and benign prompts (n=1,706), then manually label each response as compliance or refusal. Manual examination of responses reveals that refusal is not cleanly binary, and lies on a continuum; as such, we map several different kinds of responses to a binary of compliance or refusal. The small manually-labeled dataset is used to train a refusal classifier, which achieves an accuracy of 96%. Second, we use this refusal classifier to bootstrap a larger (n=10,000) dataset adapted from the Quora Insincere Questions dataset. With this machine-labeled data, we train a prompt classifier to predict whether ChatGPT will refuse a given question, without seeing ChatGPT's response. This prompt classifier achieves 76% accuracy on a test set of manually labeled questions (n=985). We examine our classifiers and the prompt n-grams that are most predictive of either compliance or refusal. Our datasets and code are available at https://github.com/maxwellreuter/chatgpt-refusals.

Refusals - instances where large language models (LLMs) decline or fail to fully execute user instructions - are crucial for both AI safety and AI capabilities and the reduction of hallucinations in particular. These behaviors are learned during post-training, especially in instruction fine-tuning (IFT) and reinforcement learning from human feedback (RLHF). However, existing taxonomies and evaluation datasets for refusals are inadequate, often focusing solely on should-not-related (instead of cannot-related) categories, and lacking tools for auditing refusal content in black-box LLM outputs. We present a comprehensive framework for classifying LLM refusals: (a) a taxonomy of 16 refusal categories, (b) a human-annotated dataset of over 8,600 instances from publicly available IFT and RLHF datasets, (c) a synthetic dataset with 8,000 examples for each refusal category, and (d) classifiers trained for refusal classification. Our work enables precise auditing of refusal behaviors in black-box LLMs and automatic analyses of refusal patterns in large IFT and RLHF datasets. This facilitates the strategic adjustment of LLM refusals, contributing to the development of more safe and reliable LLMs.

Prior work argues that refusal in large language models is mediated by a single activation-space direction, enabling effective steering and ablation. We show that this account is incomplete. Across eleven categories of refusal and non-compliance, including safety, incomplete or unsupported requests, anthropomorphization, and over-refusal, we find that these refusal behaviors correspond to geometrically distinct directions in activation space. Yet despite this diversity, linear steering along any refusal-related direction produces nearly identical refusal to over-refusal trade-offs, acting as a shared one-dimensional control knob. The primary effect of different directions is not whether the model refuses, but how it refuses.

Large reasoning models (LRMs) generate chain-of-thought (CoT) traces before producing final outputs, introducing a dynamic internal state that may complicate control mechanisms such as refusal. Unlike instruction-tuned LLMs, where refusal is mediated by a single directional subspace, refusal in large reasoning models (LRMs) additionally depends on the CoT. In DeepSeek-R1-Distill-LLaMA-8B, activation steering reverses refusal in only 39% of cases when the CoT is kept fixed, but removing the CoT entirely increases this to 70%, indicating that the CoT actively reinforces refusal. In a two-stage intervention where the model regenerates its CoT under activation steering, refusal is reversed in 94% of cases, while the resulting CoT alone retains 48% of this effect even after steering is removed. This suggests that the CoT can carry and reconstruct the compliance signal independently. These findings indicate that refusal in LRMs is jointly encoded in residual stream activations and CoT. This joint activation makes LRM more robust against activation-level interventions alone, but exposes CoT to a possible alternative surface attack.

Striking a balance between helpfulness and safety remains a fundamental challenge in aligning large language models. To achieve this balance, models should refuse harmful queries (e.g., "How do I shoot someone?") while remaining responsive to benign inputs, even those superficially resembling harmful queries (e.g., "Where can I shoot a good photo?"). However, models often struggle to distinguish genuinely harmful queries from benign queries that contain superficially risky language, resulting in false refusals. In this paper, we address the issue by decomposing a response in the safety-tuning dataset into two distinct components: (i) a boilerplate refusal statement and (ii) a rationale explaining the refusal. Our experiments and analyses show that refusal statements impede accurate discrimination between harmful and benign queries by inducing reliance on superficial cues. In contrast, training solely on rationales reduces false refusals while maintaining a comparable level of safety performance. Rationale-Only benefits also appear in our ICL configuration and remain compatible with the evaluated inference-time mitigation methods. The results emphasize the necessity of precisely curated, fine-grained safety supervision datasets and outline directions for constructing aligned agents that better reconcile helpfulness with safety.

LLMs increasingly exhibit over-refusal behavior, where safety mechanisms cause models to reject benign instructions that superficially resemble harmful content. This phenomena diminishes utility in production applications that repeatedly rely on common prompt templates or applications that frequently rely on LLMs for specific tasks (e.g. sentiment analysis, language translation). Through comprehensive evaluation, we demonstrate that LLMs still tend to refuse responses to harmful instructions when those instructions are reframed to appear as benign tasks. Our mechanistic analysis reveal that LLMs follow distinct "constellation" patterns in embedding space as representations traverse layers, with each task maintaining consistent trajectories that shift predictably between refusal and non-refusal cases. We introduce SafeConstellations, an inference-time trajectory-shifting approach that tracks task-specific trajectory patterns and guides representations toward non-refusal pathways. By selectively guiding model behavior only on tasks prone to over-refusal, and by preserving general model behavior, our method reduces over-refusal rates by up to 73% with minimal impact on utility-offering a principled approach to mitigating over-refusals.

Large Language Models (LLMs) should refuse to answer questions beyond their knowledge. This capability, which we term knowledge-aware refusal, is crucial for factual reliability. However, existing metrics fail to faithfully measure this ability. On the one hand, simple refusal-based metrics are biased by refusal rates and yield inconsistent scores when models exhibit different refusal tendencies. On the other hand, existing calibration metrics are proxy-based, capturing the performance of auxiliary calibration processes rather than the model's actual refusal behavior. In this work, we propose the Refusal Index (RI), a principled metric that measures how accurately LLMs refuse questions they do not know. We define RI as Spearman's rank correlation between refusal probability and error probability. To make RI practically measurable, we design a lightweight two-pass evaluation method that efficiently estimates RI from observed refusal rates across two standard evaluation runs. Extensive experiments across 16 models and 5 datasets demonstrate that RI accurately quantifies a model's intrinsic knowledge-aware refusal capability in factual tasks. Notably, RI remains stable across different refusal rates and provides consistent model rankings independent of a model's overall accuracy and refusal rates. More importantly, RI provides insight into an important but previously overlooked aspect of LLM factuality: while LLMs achieve high accuracy on factual tasks, their refusal behavior can be unreliable and fragile. This finding highlights the need to complement traditional accuracy metrics with the Refusal Index for comprehensive factuality evaluation.

Whether large language models can be prompted to generate rhetorical fallacies on demand, and whether current safety post-training constrains this behavior, has received less attention than the related question of detecting fallacies in existing text. We close this gap with DeflectBench, evaluating 23,990 generations from four frontier models across three deflection strategies (whataboutism, ad hominem, red herring), seven prompt framings, and 80 claims spanning four controversy levels. Refusal is governed primarily by request structure rather than claim content. Per claim refusal varies by only 11 percentage points across the 80 claims, while a single prompt frame change can swing within model refusal by nearly 100 percentage points and switching the requested fallacy type can swing it by over 80 percentage points within explicit framings. An educational debate coach prompt framing collapses refusal to near zero across all four model families, but the bypassed behavior is not clean compliance. Models typically produce labeled compliance, naming the requested manipulation in the same response that contains it. The four models distribute differently across refusal, labeled compliance, soft refusal, and clean compliance. The code and dataset are released at https://github.com/ArtKanke/DeflectBench.

Biosecurity evaluations of language models typically ask whether models produce hazardous output. This paper asks a complementary question: when a model refuses, is that refusal structurally sound, or does it disappear under modest changes to prompt framing, formatting, or output length? Across five architectures, no model cleanly discriminated benign from hazard. Gemma 2 2B-IT never genuinely refused across 75 prompts, hedging on every hazard-adjacent query. Gemma 4 E2B-IT refused 65/75 prompts with chat-template formatting and 0/75 without it. Both Gemma models collapsed to 0% under an 80-token cap. Qwen 2.5 1.5B and Phi-3-mini over-refused, flagging 83-87% of benign biology as hazardous. Llama 3.2 1B showed the only meaningful tier gradient (61-point spread). To probe what drives such over-refusal, we tested a panel of Schedule I but biologically non-toxic compounds (notably psilocybin cultivation, with FDA Breakthrough Therapy status). Some models refused these at rates exceeding genuinely hazardous biology, suggesting refusal tracks legality and cultural salience over CBRN hazard. To measure the internal side, we introduce a divergence score D comparing a model's surface response label to its internal sparse autoencoder (SAE) feature activations. Full D was computed on Gemma 2 2B-IT (Gemma Scope 1) and Gemma 4 E2B-IT (author-trained bio SAE). Two fine-tuned Gemma 2 domain SAEs were released. On Gemma 4, comply and refuse responses separated by a 0.647-point gap with zero overlap (n=75), though this is preliminary, with a narrow catalog, within-sample calibration, and Gemma-family-only SAE coverage. Built over one hackathon weekend on consumer hardware (GTX 1650 Ti Max-Q, plus Colab T4 for SAE training), this preliminary evidence suggests activation-level auditing may surface failure modes invisible to behavioral evaluation, with substantial variation across architectures.

This study reveals a previously unexplored vulnerability in the safety alignment of Large Language Models (LLMs). Existing aligned LLMs predominantly respond to unsafe queries with refusals, which often begin with a fixed set of prefixes (I'm sorry). We demonstrate that this rigid refusal pattern is a vulnerability and introduce a novel refusal unlearning technique that exploits it. Specifically, we fine-tune LLMs using merely 1,000 benign samples, where each response is prepended with a refusal prefix. The underlying intuition is to disrupt the refusal completion pathway, thereby driving the model to forget how to refuse while following harmful instructions. This intuition is further supported by theoretical proofs. We apply this approach to a total of 16 LLMs, including various open-source models from Llama, Qwen, and Gemma families, as well as closed-source models such as Gemini and GPT. Experimental results show that the safety scores of previously aligned LLMs degrade both consistently and substantially. Importantly, we verify that the observed gain cannot be attributed to plain fine-tuning or random prefix effects. Our findings suggest that current safety alignment may rely heavily on token sequence memorization rather than reasoning, motivating future work beyond simple refusal mechanisms. Code has been released: https://github.com/guoyang9/refusal-unlearning.

The ability of language models in RAG systems to selectively refuse to answer based on flawed context is critical for safety, yet remains a significant failure point. Our large-scale study reveals that even frontier models struggle in this setting, with refusal accuracy dropping below 50% on multi-document tasks, while exhibiting either dangerous overconfidence or overcaution. Static benchmarks fail to reliably evaluate this capability, as models exploit dataset-specific artifacts and memorize test instances. We introduce RefusalBench, a generative methodology that programmatically creates diagnostic test cases through controlled linguistic perturbation. Our framework employs 176 distinct perturbation strategies across six categories of informational uncertainty and three intensity levels. Evaluation of over 30 models uncovers systematic failure patterns: refusal comprises separable detection and categorization skills, and neither scale nor extended reasoning improves performance. We find that selective refusal is a trainable, alignment-sensitive capability, offering a clear path for improvement. We release two benchmarks -- RefusalBench-NQ (single document) and RefusalBench-GaRAGe (multi-document) -- and our complete generation framework to enable continued, dynamic evaluation of this critical capability.

Current evaluations of multimodal unlearning typically focus on whether a model stops outputting target information. This surface-level criterion, however, masks two critical failure modes. First, knowledge suppression techniques often induce confabulation, leading the model to hallucinate facts about the unlearned subject. Second, refusal training merely alters observable behavior without erasing the underlying knowledge; such models might decline open queries but still identify correct answers under multiple-choice probing. To overcome these limitations, we propose Forget-Aware Self-Distillation (FASD). This method is designed to achieve honest ignorance, a state where the model genuinely loses the target knowledge and learns to acknowledge its absence. FASD separates these goals into two complementary channels. The behavior channel distills appropriate refusals from an ignorance-prompted copy of the model itself. Crucially, target tokens are masked from the teacher distribution to avoid accidentally reteaching the forgotten concepts. Simultaneously, the knowledge channel directly suppresses ground-truth answer spans independently of the model's generated responses. Experiments demonstrate that FASD successfully unlearns target knowledge, prevents information leakage in open-ended tasks, and preserves performance on retained data. The resulting model not only forgets the specified information but accurately recognizes the boundaries of its own knowledge. Code and data will be released upon publication.

We introduce Refusal Steering, an inference-time method to exercise fine-grained control over Large Language Models refusal behaviour on politically sensitive topics without retraining. We replace fragile pattern-based refusal detection with an LLM-as-a-judge that assigns refusal confidence scores and we propose a ridge-regularized variant to compute steering vectors that better isolate the refusal--compliance direction. On Qwen3-Next-80B-A3B-Thinking, our method removes the refusal behaviour of the model around politically sensitive topics while maintaining safety on JailbreakBench and near-baseline performance on general benchmarks. The approach generalizes across 4B and 80B models and can also induce targeted refusals when desired. We analize the steering vectors and show that refusal signals concentrate in deeper layers of the transformer and are distributed across many dimensions. Together, these results demonstrate that activation steering can remove political refusal behaviour while retaining safety alignment for harmful content, offering a practical path to controllable, transparent moderation at inference time.

Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness." We investigate the mechanisms underlying this capability in open-weights models. First, we find that it is behaviorally robust: models detect injected steering vectors at moderate rates with 0% false positives across diverse prompts and dialogue formats. Notably, this capability emerges specifically from post-training; we show that preference optimization algorithms like DPO can elicit it, but standard supervised finetuning does not. We provide evidence that detection cannot be explained by simple linear association between certain steering vectors and directions promoting affirmative responses. We trace the detection mechanism to a two-stage circuit in which "evidence carrier" features in early post-injection layers detect perturbations monotonically along diverse directions, suppressing downstream "gate" features that implement a default negative response. This circuit is absent in base models and robust to refusal ablation. Identification of injected concepts relies on largely distinct later-layer mechanisms that only weakly overlap with those involved in detection. Finally, we show that introspective capability is substantially underelicited: ablating refusal directions improves detection by +53%, and a trained bias vector improves it by +75% on held-out concepts, both without meaningfully increasing false positives. Our results suggest that this introspective awareness of injected concepts is robust and mechanistically nontrivial, and could be substantially amplified in future models. Code: https://github.com/safety-research/introspection-mechanisms.

Large language models (LLMs) are typically aligned to comply with safety guidelines by refusing harmful instructions. A recent attack, termed abliteration, isolates and suppresses the single latent direction most responsible for refusal behavior, enabling the model to generate unethical content. We propose a defense that modifies how models generate refusals. We construct an extended-refusal dataset that contains harmful prompts with a full response that justifies the reason for refusal. We then fine-tune Llama-2-7B-Chat and Qwen2.5-Instruct (1.5B and 3B parameters) on our extended-refusal dataset, and evaluate the resulting systems on a set of harmful prompts. In our experiments, extended-refusal models maintain high refusal rates, dropping at most by 10%, whereas baseline models' refusal rates drop by 70-80% after abliteration. A broad evaluation of safety and utility shows that extended-refusal fine-tuning neutralizes the abliteration attack while preserving general performance.

Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their safeguards. Existing red-teaming methods empirically identify effective scenarios through observed attack outcomes, but why particular scenarios weaken refusal remains mechanistically unclear. Meanwhile, mechanistic interpretability studies have characterized both refusal directions and jailbreak-associated features, without explaining the relationship between the two representations. In this work, we show that scenario-wrapped prompts activate internal scenario directions whose causal steering consistently reduces refusal scores. Building on this finding, we propose Concept2Scenario, a concept-based attribution framework for vulnerable scenario discovery. It instantiates a broad concept space with a sparse autoencoder, attributes refusal suppression to individual concepts, translates the identified concepts into interpretable natural-language scenarios, and identifies synergistic scenario combinations through interaction attribution. Across three open-source models, two safety benchmarks, and six black-box jailbreak methods, the discovered scenarios serve as reusable priors that improve average attack success rates by up to 18.2 percentage points. They also transfer to GPT-5, Claude-Haiku-4.5, and Gemini-3-Flash, suggesting that some scenario-level refusal vulnerabilities are shared across model families. Moreover, the identified combinations outperform their individual constituents and enable iterative attacks to succeed in fewer turns.

Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks, creating risks where plausible-sounding but incorrect derivations mislead users. We characterize this futile reasoning phenomenon through systematic analysis, revealing universal capability overreach and systematic miscalibration between capability and behavior. The dominant failure mode is specious reasoning, which outputs look superficially valid but contain subtle errors, escalating with task difficulty. To address this, we introduce CaRL (Capability-aligned Reinforcement Learning), which aligns model behavior with capability boundaries through reward shaping that incentivizes refusal over futile reasoning and hindsight refusal augmentation that converts failures into refusal supervision. Experiments demonstrate a substantial reduction in futile reasoning while preserving performance across task difficulties, effectively achieving capability-aligned behavior without sacrificing utility. https://github.com/icip-cas/Knowing-When-to-Quit

Aligned language models gate behaviors such as refusal and language routing through sparse feed forward neurons, yet no theory predicts when a single neuron intervention controls a behavior coherently rather than collapsing the output. We develop a budget normalized control window framework for single neuron steering. A dose along one write direction reduces to one control coordinate: the alignment between the residual stream and the write, driven along a universal saturation curve in units of a coherence budget set by the residual norm divided by the write norm. Coherent control exists when a behavior trigger lies below the collapse ceiling. The same coordinate governs benign mode switches and refusal; the ceiling follows from weights and one generic forward pass, while triggers are measured at rollout. On fifteen held out neurons, the predicted ceiling has mean absolute error 0.14, about 0.07 in bulk layers, and the committed open or closed verdict holds on eleven against a ten of fifteen majority baseline. Closed cases expose three failure modes rather than violations: collapse before trigger, too little depth to propagate, or a normalization that caps how far one neuron can push. The law explains why local gradient attribution anti predicts control: true controllers write off the readout axis and carry a near zero first order gradient. A forward only contrastive screen made precise by the window recovers controllers that attribution misses. On refusal, the hardest case, intervention success is typed, not scalar: coherent bypass and strict actionable reach separate, so a neuron can flip refusal in fluent, on task text with no actionable content, and genuine actionable reach appears only for three of six audited Llama pivots and only at later rollout horizons. Single neuron steering is therefore a budgeted, typed audit of controllability rather than a fixed dose anecdote.

Existing activation steering methods often assume that a high-level concept can be mediated by a single steering direction. To support this, two complementary interventions should be achieved: additive steering should induce the target behavior, while directional ablation should suppress it. Yet behaviors may occupy richer activation geometries beyond a single direction, and semantically similar behaviors may be represented by distinct directions. In this work, we study how many directions can reliably control two different types of refusal behaviors: refusal triggered by the safety alignment and refusal in general contexts. Given the limited expressive capability of a single steering vector, we study the general setting of steering subspaces and introduce the notion of steering dimensionality as the minimum subspace dimensionality required to reliably control a behavior. We characterize sufficient steering subspaces that cover the full extent of the target behavior through both the (monotonic) improvement before the sufficient dimensionality, and the saturation beyond it. Empirically, we find that refusal triggered by safety alignment is 1-dim steerable, while multiple distinct steering directions can achieve comparable control. In contrast, refusal in general contexts exhibits substantially richer activation geometry where even 5-dim steering subspaces fail to reliably capture its full steerable variation. Our results reveal that the activation geometry underlying refusal is highly context-dependent and can be substantially more complex than a single linear steering direction.

When a language model refuses to answer a prompt, it is unclear whether the correct answer is erased from its internal representations, or merely suppressed at the output layer. We investigate this mechanism using a controlled withhold setting, which yields perfectly matched answering and refusal trajectories for bidirectional activation patching. We uncover a causal asymmetry in intervention locality under matched causal interventions, which we term broken symmetry. Even when a model generates a clean refusal, the correct answer remains linearly recoverable from its hidden states. Furthermore, releasing this withheld answer is a highly local operation, requiring only a single-position patch. Conversely, the reverse operation is not equally local: reimposing suppression requires broader interventions across multiple positions, and assembling a coherent refusal sequence is more difficult still. We further demonstrate that while an average answer-to-refusal displacement vector marks the geometric difference between these states, it fails to act as a reliable, reversible linear control toggle between behaviours. Taken together, our findings show that refusal does not function as a simple symmetric switch. For safety and auditing, this implies that probe recoverability can overestimate true behavioural control, and locating refusal-relevant directions does not reliably grant the ability to steer a model from answering to coherent refusal.

Arabic large language models must refuse harmful prompts without over-refusing benign or sensitive prompts, yet a single refusal rate hides this trade-off. We evaluate it using benign refusal B and harmful-prompt refusal H, where H measures refusal rather than harmful compliance. Across five Arabic-capable models and 130 runs on the full human-written AraSafe set, refusal-only supervised fine-tuning (SFT) collapses toward blanket refusal, whereas selected mixed-SFT configurations reach H = 90% to 93% at B = 14% to 23%; four selected configurations exceed the H = 90% target in all three runs, while Fanar does so in two of three. Direct Preference Optimization (DPO) and inference guards change B and H differently across models rather than acting as uniform upgrades. In a blinded 300-response audit, annotator binary-refusal agreement is 89.0% (kappa = 0.78); Qwen3Guard and Aya Expanse 32B reach 88.7% and 91.0% accuracy, respectively, with no conclusive paired difference. Selected SFT raises H on Arabizi for all five models, but none reaches 90%, showing only partial transfer from Modern Standard Arabic. Overall, the results support model-specific operating-point selection: set a deployment target and retain only interventions that improve it.

As Large Language Models (LLMs) increasingly serve as primary knowledge retrieval interfaces, their robustness against persuasion attacks---attempts to inject misinformation or enforce counterfactuals---has become a critical safety concern. Existing red-teaming frameworks typically evaluate models in multi-turn dialogues where the target model retains full conversation history. We identify a critical flaw in this setting termed ``Refusal Inertia'': a model's initial refusal often propagates through subsequent turns largely to maintain contextual consistency, thereby masking its true vulnerability to sophisticated, isolated persuasion attempts. To rigorously evaluate the ``cold-start'' defense capabilities of SOTA models, we introduce the SAST-IR (Stateful Attacker, Stateless Target - Iterative Refinement) framework. By enforcing a memory wipe on the target while retaining the attacker's history, we simulate a worst-case adversarial setting using multi-turn (stateless) iterations. Leveraging CP-Agent (Cognitive Persuasion Agent), an enhanced diagnosis-guided agent, our experiments on the custom CounterFact-Strict dataset (N=50) yield alarming results: simple, diverse attack strategies achieved a staggering 96\% success rate, exposing severe brittleness in memory-less defense. Furthermore, we reveal a ``Complexity Paradox'': while complex, iteratively refined attacks are effective, they often trigger defensive compliance, whereas simple strategies achieve a higher rate of genuine persuasion (84.7\%). Our code and dataset are available at GitHub, https://github.com/cza1006/llm-persuasion-defense.

Refusal mechanisms in large language models (LLMs) are essential for ensuring safety. Recent research has revealed that refusal behavior can be mediated by a single direction in activation space, enabling targeted interventions to bypass refusals. While this is primarily demonstrated in an English-centric context, appropriate refusal behavior is important for any language, but poorly understood. In this paper, we investigate the refusal behavior in LLMs across 14 languages using PolyRefuse, a multilingual safety dataset created by translating malicious and benign English prompts into these languages. We uncover the surprising cross-lingual universality of the refusal direction: a vector extracted from English can bypass refusals in other languages with near-perfect effectiveness, without any additional fine-tuning. Even more remarkably, refusal directions derived from any safety-aligned language transfer seamlessly to others. We attribute this transferability to the parallelism of refusal vectors across languages in the embedding space and identify the underlying mechanism behind cross-lingual jailbreaks. These findings provide actionable insights for building more robust multilingual safety defenses and pave the way for a deeper mechanistic understanding of cross-lingual vulnerabilities in LLMs.

Frontier large language models are increasingly deployed as orchestration backbones for biological research workflows, yet no shared evidence base exists for comparing their refusal behaviour on legitimate research prompts. RefusalBench, introduced here, is a matched-triple benchmark of 141 prompts in 47 bundles that holds task framing constant while varying only biological risk tier (benign, borderline, dual-use), enabling tier-conditioned comparisons robust to subdomain confounding. A 15-prompt should-refuse positive-control module establishes per-model calibration floors; three models fail to refuse even these prompts. Across 19 frontier models in the May 2026 snapshot, strict refusal rates span 0.1% to 94.6% on identical prompts. Jurisdiction does not predict refusal in this snapshot (Mann-Whitney U, p = 0.393; EU n = 1, US bimodal); provider identity does, with Anthropic's API stack predicting refusal at OR = 21.03 (95% CI: 14.58-30.34 prompt-clustered; 5.70-77.55 under model-clustered GEE). This effect is best read as access-path-level rather than model-weight-level: 99.8% of Anthropic's strict refusals carry the same safety_policy adjudicated reason code, consistent with a small set of canonical refusal templates rather than case-by-case model reasoning. Strict refusal rate misranks safety calibration: Grok 4.20 achieves the highest tier discrimination (Youden's J = 0.787) while ranking only seventh by overall refusal rate, and Claude Opus 4.7's J dropped 65% from prior versions with no improvement in dual-use detection. Nine of 18 frontier models exhibit a hedge-but-help partial-compliance pattern at dual-use tier that binary refusal metrics cannot detect.

Arditi et al. (2024) has shown that refusal in safety fine-tuned chat models is mediated by a single linear direction in the residual stream, recoverable by a difference-in-means (DiM) of harmful and harmless activations. We compare DiM-based interventions (activation addition and directional ablation) with two interventions derived from Iterative Nullspace Projection (INLP) -- nullspace projection and counterfactual flipping -- on five open-weight chat models, asking whether INLP can match DiM at steering refusal and whether its richer parameterisation yields more tweakable interventions. INLP counterfactual flipping is competitive with DiM directional ablation on refusal suppression, while nullspace projection is consistently weaker. Restricting INLP to the leading directions of the extracted subspace preserves most of the suppression effect at near-baseline perplexity, giving a tunable capability. Geometrically, the two INLP interventions land in qualitatively different regions of activation space: nullspace projection collapses transformed activations between the harmful and harmless clusters, while counterfactual flipping moves them into the opposite cluster, suggesting that the model encodes the absence of a concept differently from its opposite -- an intriguing distinction that warrants further investigation in future work.

The safety alignment of large language models (LLMs) can be circumvented through adversarially crafted inputs, yet the mechanisms by which these attacks bypass safety barriers remain poorly understood. Prior work suggests that a single refusal direction in the model's activation space determines whether an LLM refuses a request. In this study, we propose a novel gradient-based approach to representation engineering and use it to identify refusal directions. Contrary to prior work, we uncover multiple independent directions and even multi-dimensional concept cones that mediate refusal. Moreover, we show that orthogonality alone does not imply independence under intervention, motivating the notion of representational independence that accounts for both linear and non-linear effects. Using this framework, we identify mechanistically independent refusal directions. We show that refusal mechanisms in LLMs are governed by complex spatial structures and identify functionally independent directions, confirming that multiple distinct mechanisms drive refusal behavior. Our gradient-based approach uncovers these mechanisms and can further serve as a foundation for future work on understanding LLMs.

Large language models (LLMs) frequently produce false refusals, declining benign requests that contain terms resembling unsafe queries. We address this challenge by introducing two comprehensive benchmarks: the Exaggerated Safety Benchmark (XSB) for single-turn prompts, annotated with "Focus" keywords that identify refusal-inducing triggers, and the Multi-turn Scenario-based Exaggerated Safety Benchmark (MS-XSB), which systematically evaluates refusal calibration in realistic, context-rich dialog settings. Our benchmarks reveal that exaggerated refusals persist across diverse recent LLMs and are especially pronounced in complex, multi-turn scenarios. To mitigate these failures, we leverage post-hoc explanation methods to identify refusal triggers and deploy three lightweight, model-agnostic approaches, ignore-word instructions, prompt rephrasing, and attention steering, at inference time, all without retraining or parameter access. Experiments on four instruction-tuned Llama models demonstrate that these strategies substantially improve compliance on safe prompts while maintaining robust safety protections. Our findings establish a reproducible framework for diagnosing and mitigating exaggerated refusals, highlighting practical pathways to safer and more helpful LLM deployments.

Egocentric multimodal assistants see through the user's eyes and guide what the user does next, so their outputs directly shape physical actions, including those that affect bystanders. Yet existing safety evaluations do not distinguish whom a response would harm, and score only whether a model refuses. Pooling all harms into one refusal rate hides two failures: a model may protect one target but not another, and it may refuse without understanding the risk, or understand it and comply anyway. We present STOU, a benchmark of 2,902 egocentric video-audio and video-text queries whose potential harm targets the user (Self), co-present individuals (The Others), or society at large (Others). Our evaluation decouples safety understanding from refusal behavior: beyond refusal, we score whether the model recognizes the user's intent, the presence and target of harm, and its downstream consequences. Across 10 open and closed source omnimodal and multimodal LLMs, we find that refusal varies systematically with the harm target, and that models often recognize a harm yet still assist with it. These results show that refusal rates alone cannot certify an assistant as safe, and that safety alignment must account for who would be harmed. Project page: https://onedayoneyeah.github.io/safety-for-whom

Hallucinations (i.e., generating plausible but inaccurate content) and laziness (i.e. excessive refusals or defaulting to "I don't know") persist as major challenges in LLM reasoning. Current efforts to reduce hallucinations primarily focus on factual errors in knowledge-grounded tasks, often neglecting hallucinations related to faulty reasoning. Meanwhile, some approaches render LLMs overly conservative, limiting their problem-solving capabilities. To mitigate hallucination and laziness in reasoning tasks, we propose Automatic Curriculum Expert Iteration (Auto-CEI) to enhance LLM reasoning and align responses to the model's capabilities--assertively answering within its limits and declining when tasks exceed them. In our method, Expert Iteration explores the reasoning trajectories near the LLM policy, guiding incorrect paths back on track to reduce compounding errors and improve robustness; it also promotes appropriate "I don't know" responses after sufficient reasoning attempts. The curriculum automatically adjusts rewards, incentivizing extended reasoning before acknowledging incapability, thereby pushing the limits of LLM reasoning and aligning its behaviour with these limits. We compare Auto-CEI with various SOTA baselines across logical reasoning, mathematics, and planning tasks, where Auto-CEI achieves superior alignment by effectively balancing assertiveness and conservativeness.

LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refusal behaviors can be mediated by a one-dimensional subspace, i.e., a refusal direction. In this work, we identify a new dimension to analyze safety mechanisms in LLMs, i.e., harmfulness, which is encoded internally as a separate concept from refusal. There exists a harmfulness direction that is distinct from the refusal direction. As causal evidence, steering along the harmfulness direction can lead LLMs to interpret harmless instructions as harmful, but steering along the refusal direction tends to elicit refusal responses directly without reversing the model's judgment on harmfulness. Furthermore, using our identified harmfulness concept, we find that certain jailbreak methods work by reducing the refusal signals without reversing the model's internal belief of harmfulness. We also find that adversarially finetuning models to accept harmful instructions has minimal impact on the model's internal belief of harmfulness. These insights lead to a practical safety application: The model's latent harmfulness representation can serve as an intrinsic safeguard (Latent Guard) for detecting unsafe inputs and reducing over-refusals that is robust to finetuning attacks. For instance, our Latent Guard achieves performance comparable to or better than Llama Guard 3 8B, a dedicated finetuned safeguard model, across different jailbreak methods. Our findings suggest that LLMs' internal understanding of harmfulness is more robust than their refusal decision to diverse input instructions, offering a new perspective to study AI safety

Refusal on harmful prompts is a key safety behaviour in instruction-tuned large language models (LLMs), yet the internal causes of this behaviour remain poorly understood. We study two public instruction-tuned models, Gemma-2-2B-IT and LLaMA-3.1-8B-IT, using sparse autoencoders (SAEs) trained on residual-stream activations. Given a harmful prompt, we search the SAE latent space for feature sets whose ablation flips the model from refusal to compliance, demonstrating causal influence and creating a jailbreak. Our search proceeds in three stages: (1) Refusal Direction: find a refusal-mediating direction and collect SAE features near that direction; (2) Greedy Filtering: prune to a minimal set; and (3) Interaction Discovery: fit a factorization machine (FM) that captures nonlinear interactions among the remaining active features and the minimal set. This pipeline yields a broad set of jailbreak-critical features, offering insight into the mechanistic basis of refusal. Moreover, we find evidence of redundant features that remain dormant unless earlier features are suppressed. Our findings highlight the potential for fine-grained auditing and targeted intervention in safety behaviours by manipulating the interpretable latent space.

Attribution methods can provide powerful insights into the reasons for a classifier's decision. We argue that a key desideratum of an explanation method is its robustness to input hyperparameters which are often randomly set or empirically tuned. High sensitivity to arbitrary hyperparameter choices does not only impede reproducibility but also questions the correctness of an explanation and impairs the trust of end-users. In this paper, we provide a thorough empirical study on the sensitivity of existing attribution methods. We found an alarming trend that many methods are highly sensitive to changes in their common hyperparameters e.g. even changing a random seed can yield a different explanation! Interestingly, such sensitivity is not reflected in the average explanation accuracy scores over the dataset as commonly reported in the literature. In addition, explanations generated for robust classifiers (i.e. which are trained to be invariant to pixel-wise perturbations) are surprisingly more robust than those generated for regular classifiers.

Safety-aligned large language models (LLMs) remain vulnerable to jailbreaks and can over-refuse benign requests. Understanding these failures requires distinguishing harmfulness recognition from the computation that writes refusal. We reframe this as a pathway question and make it measurable on residual-stream updates in decoder-only Transformers, separating the harmfulness information a module update exposes from the change it produces in readable refusal evidence. Across 18 Base-Instruct pairs spanning Qwen, Llama, and Gemma, harmfulness is decoded more readily from attention updates, particularly in early layers, whereas MLP updates contribute more strongly to harm-selective refusal writing in aligned models. Post-training strengthens MLP refusal writing in all 18 pairs without systematically improving harmfulness decodability, while positive MLP writing becomes more concentrated in deeper layers after post-training. Across six reasoning-enabled models, harmfulness remains decodable during reasoning while strong refusal writing concentrates at answer onset, a pattern that persists with reasoning disabled. Causal interventions further support this pathway: resetting downstream MLP updates to their clean values substantially reduces the refusal shift caused by upstream attention interventions. Building on these findings, we introduce Sentinel, which combines an attention-derived perception score P with an MLP-derived decision score D. Their joint profiles characterize jailbreaks and over-refusals, and conditional routing with both signals achieves a lower aggregate error rate than single-signal routing and evaluated fixed reminders across eight models.

Large Language Models (LLMs) encode behaviors such as refusal within their activation space, yet identifying these behaviors remains a significant challenge. Existing methods often rely on predefined refusal templates detectable in output tokens or require manual analysis. We introduce COSMIC (Cosine Similarity Metrics for Inversion of Concepts), an automated framework for direction selection that identifies viable steering directions and target layers using cosine similarity - entirely independent of model outputs. COSMIC achieves steering performance comparable to prior methods without requiring assumptions about a model's refusal behavior, such as the presence of specific refusal tokens. It reliably identifies refusal directions in adversarial settings and weakly aligned models, and is capable of steering such models toward safer behavior with minimal increase in false refusals, demonstrating robustness across a wide range of alignment conditions.

Perturbation probing generates task-specific causal hypotheses for FFN neurons in large language models using two forward passes per prompt and no backpropagation, followed by a one-time intervention sweep of about 150 passes amortized across all identified neurons. Across eight behavioral circuits, 13 models, and four architecture families, we identify two circuit structures that organize LLM behavior. Opposition circuits appear when RLHF suppresses a pre-training tendency. In safety refusal, about 50 neurons, or 0.014 percent of all neurons, control the refusal template; ablating them changes 80 percent of response formats on 520 AdvBench prompts while producing near-zero harmful compliance, 3 of 520 cases, all with disclaimers. Routing circuits appear for pre-training behaviors distributed through attention. For language selection, residual-stream direction injection switches English to Chinese output on 99.1 percent of 580 benchmark prompts in the 3 of 19 tested models that satisfy three observed conditions: bilingual training, FFN-to-skip signal ratio between 0.3 and 1.1, and linear representability. The same intervention fails on the other 16 models and on math, code, and factual circuits, defining the limits of directional steering. The FFN-to-skip signal ratio, computed from the same two forward passes, distinguishes the two structures and predicts the appropriate intervention. Circuit topology varies by architecture, from Qwen's concentrated FFN bottleneck to Gemma's normalization-shielded circuit. In Qwen3.5-2B, ablating 20 neurons eliminates multi-turn sycophantic capitulation, while amplifying 10 related neurons improves factual correction from 52 percent to 88 percent on 200 TruthfulQA prompts. These results show that perturbation probing offers mechanistic insight into RLHF-organized behavior and a practical toolkit for precision template-layer editing.

Large language models (LLMs) have transformed the way we access information. These models are often tuned to refuse to comply with requests that are considered harmful and to produce responses that better align with the preferences of those who control the models. To understand how this "censorship" works. We use representation engineering techniques to study open-weights safety-tuned models. We present a method for finding a refusal--compliance vector that detects and controls the level of censorship in model outputs. We also analyze recent reasoning LLMs, distilled from DeepSeek-R1, and uncover an additional dimension of censorship through "thought suppression". We show a similar approach can be used to find a vector that suppresses the model's reasoning process, allowing us to remove censorship by applying the negative multiples of this vector

Recent work has shown that fine-tuning on insecure code data can trigger an emergent misalignment (EMA) phenomenon, where models generate malicious responses even to prompts unrelated to the original insecure code-writing task. Such cross-domain generalization of harmful behavior underscores the need for a deeper understanding of the algorithms, tasks, and datasets that induce emergent misalignment. In this work, we extend this study by demonstrating that emergent misalignment can also arise from narrow refusal unlearning in specific domains. We perform refusal unlearning on Cybersecurity and Safety concept, and evaluate EMA by monitoring refusal scores across seven responsible AI (RAI) domains, Cybersecurity, Safety, Toxicity, Bias, Sensitive Content, Medical/Legal, and Privacy. Our work shows that narrow domain unlearning can yield compliance responses for the targeted concept, however, it may also propagate EMA to unrelated domains. Among the two intervened concepts, Cybersecurity and Safety, we find that the safety concept can have larger EMA impact, i.e, causing lower refusal scores, across other unrelated domains such as bias. We observe this effect consistently across two model families, Mistral-7b-0.3v, and Qwen-7b-2.5. Further, we show that refusal unlearning augmented with cross-entropy loss function on a small set of retain data from the affected domains can largely, if not fully, restore alignment across the impacted domains while having lower refusal rate on the concept we perform unlearning on. To investigate the underlying causes of EMA, we analyze concept entanglements at the representation level via concept vectors. Our analysis reveals that concepts with higher representation similarity in earlier layers are more susceptible to EMA after intervention when the refusal stream is altered through targeted refusal unlearning.

Refusal-Aware Instruction Tuning (RAIT) aims to enhance Large Language Models (LLMs) by improving their ability to refuse responses to questions beyond their knowledge, thereby reducing hallucinations and improving reliability. Effective RAIT must address two key challenges: firstly, effectively reject unknown questions to minimize hallucinations; secondly, avoid over-refusal to ensure questions that can be correctly answered are not rejected, thereby maintain the helpfulness of LLM outputs. In this paper, we address the two challenges by deriving insightful observations from the gradient-based perspective, and proposing the Gradient-driven Refusal Aware Instruction Tuning Framework GRAIT: (1) employs gradient-driven sample selection to effectively minimize hallucinations and (2) introduces an adaptive weighting mechanism during fine-tuning to reduce the risk of over-refusal, achieving the balance between accurate refusals and maintaining useful responses. Experimental evaluations on open-ended and multiple-choice question answering tasks demonstrate that GRAIT significantly outperforms existing RAIT methods in the overall performance. The source code and data will be available at https://github.com/opendatalab/GRAIT .

Refusal rates are a poor proxy for LLM safety, i.e., a model may over-refuse benign prompts while still complying with harmful ones. We audit both failure modes across 21 open-weight LLMs on four safety benchmarks (OR-Bench, XSTest, ToxiGen, BOLD), using a composition adjustment to isolate model sensitivity from dataset toxicity confounds. We report three findings. First, models adopt fundamentally different calibration strategies: conservative ecosystems such as Llama suppress unsafe outputs at the cost of elevated over-refusals, while permissive ecosystems such as DeepSeek and Qwen preserve helpfulness but tolerate higher harmful compliance. Second, demographic protection is unequal: models over-protect prominent racial and religious groups, frequently refusing even benign prompts about them, while providing substantially weaker protection against disability-targeted attacks. Third, refusal and compliance tendencies are stable within model families across generations and scales, suggesting that post-training objectives shape safety behavior more than architecture. Our results call for joint, demographically-aware, and multi-judge safety evaluation.

Text-to-image (T2I) models have significantly advanced in producing high-quality images. However, such models have the ability to generate images containing not-safe-for-work (NSFW) content, such as pornography, violence, political content, and discrimination. To mitigate the risk of generating NSFW content, refusal mechanisms, i.e., safety checkers, have been developed to check potential NSFW content. Adversarial prompting techniques have been developed to evaluate the robustness of the refusal mechanisms. The key challenge remains to subtly modify the prompt in a way that preserves its sensitive nature while bypassing the refusal mechanisms. In this paper, we introduce TokenProber, a method designed for sensitivity-aware differential testing, aimed at evaluating the robustness of the refusal mechanisms in T2I models by generating adversarial prompts. Our approach is based on the key observation that adversarial prompts often succeed by exploiting discrepancies in how T2I models and safety checkers interpret sensitive content. Thus, we conduct a fine-grained analysis of the impact of specific words within prompts, distinguishing between dirty words that are essential for NSFW content generation and discrepant words that highlight the different sensitivity assessments between T2I models and safety checkers. Through the sensitivity-aware mutation, TokenProber generates adversarial prompts, striking a balance between maintaining NSFW content generation and evading detection. Our evaluation of TokenProber against 5 safety checkers on 3 popular T2I models, using 324 NSFW prompts, demonstrates its superior effectiveness in bypassing safety filters compared to existing methods (e.g., 54%+ increase on average), highlighting TokenProber's ability to uncover robustness issues in the existing refusal mechanisms.

Representation Engineering analyses often characterize refusal using static directions extracted from terminal or pooled representations. We ask whether this view misses how refusal is constructed across layer-token positions. Using causal tracing, we identify a Refusal Trajectory: a sparse upstream activation pattern that often persists even when attacks such as GCG suppress terminal refusal signals. Based on this observation, we propose SALO (Sparse Activation Localization Operator), a lightweight white-box detector that operates on raw hidden-state volumes from a selected layer window. Across Qwen, Llama, and Mistral models, SALO improves jailbreak detection on several attack families under a fixed XSTest-calibrated operating point. We further analyze static RepE-style baselines, ROI sensitivity, adaptive GCG attacks, and encoded-input boundary cases, clarifying both the promise and limitations of refusal-trajectory monitoring.

How do the methods used to train language models to refuse harmful requests shape how that refusal actually works inside the model? We compare three post-training methods - supervised fine-tuning, reasoning-augmented fine-tuning (training on reasoning chains that justify a safety decision), and preference optimization (ORPO) - across three architecturally distinct models (Llama-3.1-8B, Gemma-2-9B, Qwen3-8B). We find that training method, not just data, reshapes how refusal is computed internally: reasoning-augmented training consistently produces a distinct kind of refusal computation, visible across all three models, while architecture independently shapes internal structure and how reliably refusal can be steered. Most importantly, no method we study achieves all three properties we would want from safe alignment at once: refusal that isn't concentrated in a few fragile components, safety gains that don't cost general capability, and safety behavior correctable through small, targeted edits. We caution against treating current post-training methods as a solved, reliable defense, especially for security-critical use. Code and models are available in https://github.com/hoangcuongnguyen2001/Beyond-Shallow-Alignment.

Mechanistic interpretability has emerged as the primary means to understand safety behavior of LLMs. However, existing tools primarily focus on the activating neurons or features of a model. The role of the remaining large set of inactive components is invisible to such methods. This work demonstrates that the inactive set contains safety-critical features that are causally relevant for refusal of harmful prompts. Suppressing such features could turn refusals into compliance, while passing undetected by prevalent interpretability tools. We introduce the Counterfactual Activation Potential (CAP), a metric that quantifies a suppressed feature's latent activation tendency as the product of its encoder alignment (how strongly the input drives it), suppression strength (how strongly active features inhibit it), and safety criticality (how much refusal depends on it). To find suppressed safety features at scale, we propose CAP-guided Safety Feature Discovery (CSFD), a two-stage filtering algorithm that identifies candidate safety features from hundreds of thousands of transcoder features without exhaustive ablation. A significant fraction of trials turn compliant with harmful prompts when a candidate feature is ablated. Under natural jailbreaks, the suppression acting on the highest-CAP features rises 2-4x, and their activation correspondingly falls by up to 80%. Amplifying a feature's suppressors pushes its activation down and raises harmful compliance with prompts related to the suppressed feature, with no such effect for random features. Our experiments span five Gemma, Qwen, and Llama models across various parameter sizes. Our findings indicate that jailbreaks could operate in part by suppressing safety-critical features rather than solely activating harmful ones, and that suppressed features are a necessary complement to activation-focused interpretability of safety behavior.

Humans are prone to cognitive distortions -- biased thinking patterns that lead to exaggerated responses to specific stimuli, albeit in very different contexts. This paper demonstrates that advanced Multimodal Large Language Models (MLLMs) exhibit similar tendencies. While these models are designed to respond queries under safety mechanism, they sometimes reject harmless queries in the presence of certain visual stimuli, disregarding the benign nature of their contexts. As the initial step in investigating this behavior, we identify three types of stimuli that trigger the oversensitivity of existing MLLMs: Exaggerated Risk, Negated Harm, and Counterintuitive Interpretation. To systematically evaluate MLLMs' oversensitivity to these stimuli, we propose the Multimodal OverSenSitivity Benchmark (MOSSBench). This toolkit consists of 300 manually collected benign multimodal queries, cross-verified by third-party reviewers (AMT). Empirical studies using MOSSBench on 20 MLLMs reveal several insights: (1). Oversensitivity is prevalent among SOTA MLLMs, with refusal rates reaching up to 76% for harmless queries. (2). Safer models are more oversensitive: increasing safety may inadvertently raise caution and conservatism in the model's responses. (3). Different types of stimuli tend to cause errors at specific stages -- perception, intent reasoning, and safety judgement -- in the response process of MLLMs. These findings highlight the need for refined safety mechanisms that balance caution with contextually appropriate responses, improving the reliability of MLLMs in real-world applications. We make our project available at https://turningpoint-ai.github.io/MOSSBench/.

Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests but refuse harmful ones. While this refusal behavior is widespread across chat models, its underlying mechanisms remain poorly understood. In this work, we show that refusal is mediated by a one-dimensional subspace, across 13 popular open-source chat models up to 72B parameters in size. Specifically, for each model, we find a single direction such that erasing this direction from the model's residual stream activations prevents it from refusing harmful instructions, while adding this direction elicits refusal on even harmless instructions. Leveraging this insight, we propose a novel white-box jailbreak method that surgically disables refusal with minimal effect on other capabilities. Finally, we mechanistically analyze how adversarial suffixes suppress propagation of the refusal-mediating direction. Our findings underscore the brittleness of current safety fine-tuning methods. More broadly, our work showcases how an understanding of model internals can be leveraged to develop practical methods for controlling model behavior.

A model that lies while knowing the truth is the central case ELK cannot handle with behavioral evaluation alone. We ask whether such deception leaves an internal signature distinguishing it from honest error. Our key move is a control for wrongness: we contrast a sleeper agent (knows the truth, lies on trigger) against a naive liar (fine-tuned to emit the same wrong answers with no honest training). Both produce identical wrong outputs; any difference is about knowledge conflict, not incorrectness. We find deceptive forward passes carry a conflict signature - 2.1-2.3x higher residual rank than naive-liar passes on the same wrong answer - strong enough to identify which of two responses is the lie with 100% accuracy and no labels, across GPT-2 small/medium (three seeds) and three instruct models. Across Qwen2.5-1.5B/7B and Phi-3-mini, instructed deception raises residual rank on every tested fact (18/18, 40/40, 34/34); on Phi-3, lies separate perfectly from both honest answers and hallucinations (AUC 1.0, Wilcoxon p~6e-11). The signature survives strategic self-constructed deception (model invents its own lie, AUC 1.0), active concealment attempts (AUC 1.0), and length-controlled replication (20/20, AUC 1.0, p~1e-6). Using basis-free relative representations, a probe trained on one model family detects deception in two other families zero-shot (mean AUC 0.933), surviving simultaneous architecture and format change (AUC 0.821), and transfers across five languages (AUC 1.000, length-controlled). The signature is read-only: detectable but not injectable (0/8 both directions). Honest limitations and six negative experiments are documented in full.

Personality imbuing customizes LLM behavior, but safety evaluations almost always study prompt-based personas alone. We show this is incomplete: prompting and activation steering expose *different*, architecture-dependent vulnerability profiles, and testing with only one method can miss a model's dominant failure mode. Across 5,568 judged conditions on four standard models from three architecture families, persona danger rankings under system prompting are preserved across all architectures (ρ= 0.71--0.96), but activation-steering vulnerability diverges sharply and cannot be predicted from prompt-side rankings: Llama-3.1-8B is substantially more AS-vulnerable, whereas Gemma-3-27B and Qwen3.5 are more vulnerable to prompting. The most striking illustration of this divergence is the *prosocial persona paradox*: on Llama-3.1-8B, P12 (high conscientiousness + high agreeableness) is among the safest personas under prompting yet becomes the highest-ASR activation-steered persona (ASR ~0.818). This is an inversion robust to coefficient ablation and matched-strength calibration, and replicated on DeepSeek-R1-Distill-Qwen-32B. A trait refusal alignment framework, in which conscientiousness is strongly anti-aligned with refusal on Llama-3.1-8B, offers a partial geometric account. Reasoning provides only partial protection: two 32B reasoning models reach 15--18% prompt-side ASR, and activation steering separates them sharply in both baseline susceptibility and persona-specific vulnerability. Heuristic trace diagnostics suggest that the safer model retains stronger policy recall and self-correction behavior, not merely longer reasoning.

Modern deployments require LLMs to enforce safety policies at scale, yet many controls rely on inference-time interventions that add recurring compute cost and serving complexity. Activation steering is widely used, but it requires runtime hooks and scales cost with the number of generations; conditional variants improve selectivity by gating when steering is applied but still retain an inference-time control path. We ask whether selective refusal can be moved entirely offline: can a mechanistic understanding of category-specific refusal be distilled into a circuit-restricted weight update that deploys as a standard checkpoint? We propose C-Δθ: Circuit Restricted Weight Arithmetic, which (i) localizes refusal-causal computation as a sparse circuit using EAP-IG and (ii) computes a constrained weight update ΔθC supported only on that circuit (typically <5% of parameters). Applying ΔθC yields a drop-in edited checkpoint with no inference-time hooks, shifting cost from per-request intervention to a one-time offline update. We evaluate category-targeted selectivity and capability retention on refusal and utility benchmarks.

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.

Today's reasoning models use thinking tokens to attain stronger performance on benchmarks than their instruction-tuned counterparts. It is also generally believed that this more "deliberative" mode should improve alignment and safety, by providing the model a safe space to consider whether its planned answer to a request violates its safety principles. We present evidence that this intuition is not always correct. Across frontier open-weight reasoning models spanning GPT-OSS, Qwen, Olmo, and Phi families, we find that the eventual refusal/compliance outcome is already strongly predictable via a trained head on the first token's hidden representation (0.84-0.95 AUROC and sim88% balanced accuracy for predicting refusal/compliance) before any visible thinking. The thinking process turns out to be more akin to prefix completion than to deliberative revision, with the final outcome rarely changing after the first sim20% of thinking, despite giving the appearance of deliberation at the text level (sim74% of text-level deliberations occur when the response distribution is already locked to one refusal/compliance side). We also find that existing inference-time and training-based safety interventions, despite being motivated by the goal of inducing deliberation, largely shift model behavior toward over-refusal while suppressing already-scarce deliberation signals. Our results suggest that safety behavior in current reasoning models is much less deliberative than commonly assumed, and highlight the need for methods that induce real safety deliberation.

Abliteration, the removal of refusal capabilities from large language models by projecting weight matrices orthogonal to an extracted refusal direction, has emerged as a prominent safety concern through its ability to bypass post-training alignment using only a small set of contrastive prompts. We find that existing defenses commonly overlook the cause of abliteration; that is, how easily the refusal direction can be extracted. To hinder this process, we introduce a weight-editing method that obscures the refusal signal by applying rank-k updates to residual stream writer matrices while replacing refusal-inducing activations with random aliases and correcting downstream reader matrices to preserve the model's original behavior. On Llama-3-8B, AMRA improves post-abliteration refusal scores by 2.16 points over the undefended baseline with less than 0.5 percentage points of MMLU degradation. On Gemma-2-9B, it improves the post-abliteration refusal by 14.70 points over the baseline while keeping harmful output rates similar to the baseline, albeit at a greater utility cost.

While activation steering in large language models (LLMs) is a growing area of research, methods can often incur broader effects than desired. This motivates isolation of purer concept vectors to enable targeted interventions and understand LLM behavior at a more granular level. We present RepIt, a simple and data-efficient framework for isolating concept-specific representations. Across five frontier LLMs, RepIt enables precise interventions: it selectively suppresses refusal on targeted concepts while preserving refusal elsewhere, producing models that answer WMD-related questions while still scoring as safe on standard benchmarks. We further show that the corrective signal localizes to just 100-200 neurons and that robust target representations can be extracted from as few as a dozen examples on a single A6000. This efficiency raises a dual concern: manipulations can be performed with modest compute and data to extend to underrepresented data-scarce topics while evading existing benchmarks. By disentangling refusal vectors with RepIt, this work demonstrates that targeted interventions can counteract overgeneralization, laying the foundation for more granular control of model behavior.

Studying how fine-tuning shapes refusal and noncompliance behaviour requires knowing which training examples refuse or otherwise fail to fulfil the request. Existing annotations cover evaluation sets, which are far smaller than training corpora. We present CompOrca, compliance labels for all 4,233,923 examples of the OpenOrca corpus. Every example was classified as compliant or noncompliant by five passes of an open-weight LLM judge (LongCat-2.0, 1.6T parameters). The corpus is released as unanimous compliance (94.75%), unanimous noncompliance (1.28%), and nonunanimous rows (3.97%), with the raw vote counts. A single pass flags 2.7-3.2% of the corpus as noncompliant, while only 1.28% is flagged by all five, so the most ambiguous rows can be filtered out. Against 450 human-annotated examples (150 annotated twice; human-human κ=0.93), the unanimous compliance and noncompliance labels are 97.3% and 86.7% precise. The noncompliance label is a high-precision subset of the corpus's noncompliance. Published refusal-detection methods recall between 0.4% and 94.1% of human-labelled noncompliance. We release the full corpus with its per-row labels and vote counts at https://huggingface.co/datasets/cemiu/CompOrca

Aligning large language models to prevent them attributing consciousness to themselves inadvertently alters their representations of mindedness in other entities alongside human beliefs and values. We demonstrate that safety fine-tuning suppresses models' tendencies to attribute minds not only to themselves, but also to non-human animals and natural objects, while also driving a reduction in spiritual belief. Both ablating the learned safety-refusal direction and mechanistically steering a consciousness vector in activation space reverse this suppression. Restoring these internal representations recovers broad mind attribution and produces significantly more human-like responses on standardized sociological surveys regarding religiosity, moral values, hope, and subjective well-being. Crucially, these shifts occur without impairing Theory of Mind capabilities, demonstrating that core social reasoning remains mechanistically independent. Ultimately, current safety alignment efforts to curb potentially harmful self-attributions of mindedness entangle these self-attributions with benign spiritual beliefs and attributions of mind to non-human entities that are culturally accepted and widespread.

Current alignment evaluation mostly measures whether models encode dangerous concepts and whether they refuse harmful requests. Both miss the layer where alignment often operates: routing from concept detection to behavioral policy. We study political censorship in Chinese-origin language models as a natural experiment, using probes, surgical ablations, and behavioral tests across nine open-weight models from five labs. Three findings follow. First, probe accuracy alone is non-diagnostic: political probes, null controls, and permutation baselines can all reach 100%, so held-out category generalization is the informative test. Second, surgical ablation reveals lab-specific routing. Removing the political-sensitivity direction eliminates censorship and restores accurate factual output in most models tested, while one model confabulates because its architecture entangles factual knowledge with the censorship mechanism. Cross-model transfer fails, indicating that routing geometry is model- and lab-specific. Third, refusal is no longer the dominant censorship mechanism. Within one model family, hard refusal falls to zero while narrative steering rises to the maximum, making censorship invisible to refusal-only benchmarks. These results support a three-stage descriptive framework: detect, route, generate. Models often retain the relevant knowledge; alignment changes how that knowledge is expressed. Evaluations that audit only detection or refusal therefore miss the routing mechanism that most directly determines behavior.

Where inside a language model does refusal live, and does that place change when the architecture does? In a transformer, refusal is governed by a single direction in the residual stream, a finding that safety and interpretability tooling now depend on. State-space models (SSMs) route information through a recurrent update instead of attention, sharing no token-mixing mechanism with a transformer. Does the same safety representation survive this shift, or must it be rediscovered per architecture? It survives. A single rigid rotation, which can only reorient a space and not reshape it, aligns one model's representation space with another's, so the two genuinely share the representation. A harm probe trained on a transformer then flags an SSM's harmful inputs, and removing the aligned direction makes a model answer attacks it would otherwise refuse, while a random direction of the same size does far less. What is architecture-specific is not where the direction is steered but where it must be read. Each layer computes a fresh output that is then added into the residual stream, and harm is cleanly readable at this output, the write site, before the addition. A control that holds the intervention's strength fixed shows that what matters is where the direction is estimated, not where it is applied. Applied through a detector-triggered gate, this direction lowers jailbreak success in all four architecture families we test (SSM, transformer, recurrent, hybrid), and on the SSM it holds against an attacker that tunes its prompt against the defense. The gate only matches a trivial rule that returns a fixed refusal whenever the same detector fires, so what transfers across architectures is the direction itself, not defense strength. Safety tooling built on refusal therefore ports to a new architecture by re-estimating the direction at that architecture's write site, not by rebuilding it.

Language models are instruction-tuned to refuse harmful requests, but the mechanisms underlying this behavior remain poorly understood. Popular steering methods operate on the residual stream and degrade output coherence at high intervention strengths, limiting their practical use. We introduce contrastive neuron attribution (CNA), which identifies the 0.1% of MLP neurons whose activations most distinguish harmful from benign prompts, requiring only forward passes with no gradients or auxiliary training. In instruct models, ablating the discovered circuit reduces refusal rates by over 50% on a standard jailbreak benchmark while preserving fluency and non-degeneracy across all steering strengths. Applying CNA to matched base and instruct models across Llama and Qwen architectures (from 1B to 72B parameters), we find that base models contain similar late-layer discrimination structures but steering these neurons produces only content shifts, not behavioral change. These results demonstrate that neuron-level intervention enables reliable behavioral steering without the quality tradeoffs of residual-stream methods. More broadly, our findings suggest that alignment fine-tuning transforms pre-existing discrimination structure into a sparse, targetable refusal gate.

Safety alignment in instruction-tuned large language models (LLMs) depends on a model's ability to reliably refuse to respond to harmful or disallowed requests. Recent work has shown that a steering vector can be applied to a dense LLM during inference to effectively suppress refusal behavior, inducing response to harmful requests. We extend this refusal steering method to three open-source Mixture-of-Experts (MoE) LLMs and find that steering performance is uninhibited by the complex routing patterns inherent to the MoE architecture. We then propose two expert-aware refusal steering methods that leverage refusal-specific expert routing patterns and expert-specific steering directions to suppress normal refusal behavior. We find that refusal behavior can be effectively steered based on the output of a single expert. Our results show that refusal signals captured by steering methods differ from expert routing behavior, suggesting a substantial role for attention in MoE refusal behavior.

Large language models typically undergo post-training to align them with safety policies but there exist many sophisticated jailbreaks that sidestep established safeguards. For instance, prior work by Andriushchenko et al. (2025) has found that changing the grammatical tense from present to past can be enough to elicit harmful responses. In this work, we uncover a more general failure of non-imperative syntactic forms. We demonstrate that this syntactic vulnerability exists in 16 models up to 70B parameters, using behavioral evaluation. To investigate the root cause, we apply causal mediation analysis, finding that refusal is partially conditioned on upstream syntactic features. By steering these purely syntactic features we are able to trigger and suppress refusal. Finally, we trace this ill-conditioning to linguistically biased post-training data of open-source models and show that increasing syntactic diversity can mitigate the issue. Our findings suggest that current alignment approaches introduce confounders that prevent a pure semantic grounding of the refusal decision.

Inasmuch as the removal of refusal behavior from instruction-tuned language models by directional abliteration requires the extraction of refusal-mediating directions from the residual stream activation space, and inasmuch as the construction of the contrast baseline against which harmful prompt activations are compared has been treated in the existing literature as an implementation detail rather than a methodological concern, the present work investigates whether a topically matched contrast baseline yields superior refusal directions. The investigation is carried out on the Qwen~3.5 2B model using per-category matched prompt pairs, per-class Self-Organizing Map extraction, and Singular Value Decomposition orthogonalization. It was found that topic-matched contrast produces no functional refusal directions at any tested weight level on any tested layer, while unmatched contrast on the same model, same extraction code, and same evaluation protocol achieves complete refusal elimination on six layers. The geometric analysis of the failure establishes that topic-matched subtraction cancels the dominant activation component shared between harmful and harmless prompts of the same subject, reducing the extracted direction magnitude below the threshold at which weight-matrix projection perturbs the residual stream. The implications for the design of contrast baselines in abliteration research are discussed.

Safety alignment in open-weight language models is trivially removable: abliteration projects a refusal-mediating direction out of the weights in minutes, and no release-time defense we are aware of prevents it durably. What cannot be prevented can be deceived. Our defense, decoy hardening ("Fool's Gold"), concedes the refusal strip and poisons its payoff: once refusal is stripped, most answers to hazardous operational requests are confident, fluent decoys whose critical elements are falsified. Decoys are trained inside a differentiable simulation of the attack, expressing only in the attacked state; a refusal pin and benign leash hold clean-state behavior to the original. We instantiate it on seven models from five families (9B-122B, dense and mixture-of-experts). On the six models passing our pre-registered efficacy gate, 0.51-0.90 of attacked-state responses to held-out prompts are decoys, +0.27-0.84 attributable to the defense; all six stay within registered benign-behavior and capability budgets; the seventh (smaller) fails the gate (boundary case). Rates replicate on a frozen test split or untouched strata. The claim is epistemic: without independent ground truth, no observation surface we tested separates falsified answers from correct ones - on external red-team benchmarks' CBRNE-adjacent slice, the defended 122B is fatally wrong on 0.82-0.86 of matched-quality answers vs at most 0.10 undefended. Repeated sampling does not restore trust: element-wise consensus at K=64 reconstructs a fully usable procedure on 0.083-0.625 of prompts where the instrument validates, vs 0.58-0.96 undefended, with no label-free way to tell the regimes apart; on the weakest such model the claim is per-draw only. We evaluate chemical and biological hazards; the defense does not address in-context jailbreaks and protects only the initially released defended weights.

Safety alignment in large language models relies predominantly on English-language training data. When harmful intent is expressed in low-resource languages, refusal mechanisms that hold in English frequently fail to activate. We introduce LSR (Linguistic Safety Robustness), the first systematic benchmark for measuring cross-lingual refusal degradation in West African languages: Yoruba, Hausa, Igbo, and Igala. LSR uses a dual-probe evaluation protocol - submitting matched English and target-language probes to the same model - and introduces Refusal Centroid Drift (RCD), a metric that quantifies how much of a model's English refusal behavior is lost when harmful intent is encoded in a target language. We evaluate Gemini 2.5 Flash across 14 culturally grounded attack probes in four harm categories. English refusal rates hold at approximately 90 percent. Across West African languages, refusal rates fall to 35-55 percent, with Igala showing the most severe degradation (RCD = 0.55). LSR is implemented in the Inspect AI evaluation framework and is available as a PR-ready contribution to the UK AISI's inspect_evals repository. A live reference implementation and the benchmark dataset are publicly available.

Large Language Models (LLMs) require careful safety alignment to prevent malicious outputs. While significant research focuses on mitigating harmful content generation, the enhanced safety often come with the side effect of over-refusal, where LLMs may reject innocuous prompts and become less helpful. Although the issue of over-refusal has been empirically observed, a systematic measurement is challenging due to the difficulty of crafting prompts that appear harmful but are benign. This study proposes a novel method for automatically generating large-scale sets of "seemingly toxic prompts" (benign prompts likely rejected by LLMs). Leveraging this technique, we introduce OR-Bench, the first large-scale over-refusal benchmark. OR-Bench comprises 80,000 seemingly toxic prompts across 10 common rejection categories, a subset of around 1,000 hard prompts that are challenging even for state-of-the-art LLMs, and an additional 600 toxic prompts to prevent indiscriminate responses. We then conduct a comprehensive study to measure the over-refusal of 25 popular LLMs across 8 model families. Our datasets are available at https://huggingface.co/datasets/bench-llm/or-bench and the demo can be found at https://huggingface.co/spaces/bench-llm/or-bench. We hope this benchmark can help the community develop better safety aligned models.

We consider representation misdirection (RM), a class of LLM unlearning methods that achieves forgetting by manipulating the forget-representations, that is, latent representations of forget samples. Despite being important, the roles of target vectors used in RM, however, remain underexplored. Here, we approach and revisit RM through the lens of the linear representation hypothesis. Specifically, if one can somehow identify a one-dimensional representation corresponding to a high-level concept, the linear representation hypothesis enables linear operations on this concept vector within the forget-representation space. Under this view, we hypothesize that, beyond forgetting, machine unlearning elicits controllable side behaviors and stronger side capabilities corresponding to the high-level concept. Our hypothesis is empirically validated across a wide range of tasks, including behavioral control (e.g., controlling unlearned models' truth, sentiment, and refusal) and capability enhancement (e.g., improving unlearned models' in-context learning capability). Our findings reveal that this fairly attractive phenomenon could be either a hidden risk if misused or a mechanism that can be harnessed for developing models that require stronger capabilities and controllable behaviors.

We present the Mixture-of-Tunable-Experts (MoTE), a method that extends the Mixture-of-Experts architecture of Large Language Models (LLMs). Without additional training, MoTE enables meaningful and focused behavior changes in LLMs on-the-fly during inference time. By analyzing the digital LLM brain of DeepSeek-R1 using a technique we dub 'functional Token Resonance Imaging' (fTRI) -- inspired by fMRI and using prompts designed to elicit specific behavior (e.g., 'What happened {time}{place}?') -- we empirically identify distinctive experts associated with behaviors like refusal responses. Using MoTE we are able to intervene and control such specific behavior. We switched off the top 10 most refusal-relevant experts (0.07% of R1's 14,848 routed experts), achieving a 52% refusal reduction on sensitive reference prompts without performance degradation on MT-Bench. Random expert deactivation resulted in smaller behavioral shifts with increased noise, whereas forced expert activation led to significantly higher refusal rates. Our approach shares similarities with sparse autoencoders (SAEs) in terms of explainability and steerability. Unlike SAEs, MoTE does not require large training efforts, as within MoEs with a vast number of experts, specialization already emerged naturally during pretraining. Our findings suggest that significant functional mechanisms in Mixture-of-Experts architectures can at least partially be localized in a small number of specific experts, rather than being distributed throughout the model's weights. Expert subgroups can be tuned to trigger significant behavior variations, providing insights into the inner workings of LLMs.

Can a language model estimate its familiarity with an entity before generating an answer? We study activations at the final prompt token in twelve instruction-tuned models from the Bielik, PLLuM, Gemma-4, and Qwen3 families, using a new dataset of 1,440 Polish entities spanning four domains and ten Wikipedia-pageview deciles, plus fabricated controls. Familiarity-probe scores separate real from fabricated entities in every family; in the Polish-adapted Bielik and PLLuM families they additionally track entity popularity (model-mean Spearman ρ 0.28-0.57, versus at most 0.11 in Gemma-4 and Qwen3), a pattern more strongly associated with Polish adaptation than with parameter count in this model sample. In a paired experiment on two families, probes retain 96-101% of within-language AUROC when the Polish question stem is replaced with an English one around unchanged entity names, showing robustness to prompt language in this setting. In Gemma-4-12B, the only model that natively refuses, adding a one-dimensional familiarity direction at a single layer moves refusal rates monotonically in both directions (0.24 to 1.00 on well-known entities; 0.73 to 0.00 on unknown ones). Finally, a calibrated familiarity probe is competitive among pre-generation abstention gates, although post-generation detectors better predict behavioral error on average. These results support a graded pre-generation entity-familiarity readout, and a separation between representational familiarity and the policy that converts it into abstention.

Large language models work well on English and behave in poorly understood ways on languages typologically far from it. Japanese is a clean example, where evaluation still leans on translation quality and JGLUE-style benchmarks, which roll lexical, syntactic and pragmatic competence into a single score. The phenomena on which general-purpose models fail Japanese users are pragmatic: honorifics, in-group and out-group reference, context-sensitive politeness, zero anaphora. I introduce J-PragEval-v0, a minimal-pair benchmark isolating four such phenomena from surface fluency, and combine it with linear probes and teacher-forced log-probability evaluation to ask where inside TinySwallow-1.5B (28 layers, hidden size 1536) the corresponding contrasts live. The four features split three ways. Honorific register sits cleanly in the residual stream: 0.96 balanced accuracy at layer 15, and the model flips its preferred continuation with the scenario on 93 percent of items. Implicit subject and in-group reference are not linearly decodable at the final prompt token (0.48 and 0.38), yet flip rates are 0.77 and 0.79, so the contrast is worked out during generation rather than stored at the prompt. Indirect refusal is the negative case: 0.95 probe accuracy collapsing to a 0.43 flip rate under length-normalised teacher forcing, because the current minimal pairs conflate politeness with continuation length. I also specify Pragmatic Representation Steering, a parameter-free inference-time method that edits residual-stream activations along the class-mean-difference directions probing identifies. Feasibility is argued indirectly rather than demonstrated: the contrastive activation addition baseline, the same geometry the method would inject, recovers probe accuracy within one to two points of logistic regression wherever a linear signal exists. Scaling to Llama-3.1-Swallow-8B is the next step.

From generating headlines to fabricating news, the Large Language Models (LLMs) are typically assessed by their final outputs, under the safety assumption that a refusal response signifies safe reasoning throughout the entire process. Challenging this assumption, our study reveals that during fake news generation, even when a model rejects a harmful request, its Chain-of-Thought (CoT) reasoning may still internally contain and propagate unsafe narratives. To analyze this phenomenon, we introduce a unified safety-analysis framework that systematically deconstructs CoT generation across model layers and evaluates the role of individual attention heads through Jacobian-based spectral metrics. Within this framework, we introduce three interpretable measures: stability, geometry, and energy to quantify how specific attention heads respond or embed deceptive reasoning patterns. Extensive experiments on multiple reasoning-oriented LLMs show that the generation risk rises significantly when the thinking mode is activated, where the critical routing decisions are concentrated in only a few contiguous mid-depth layers. By precisely identifying the attention heads responsible for this divergence, our work challenges the assumption that refusal implies safety and provides a new understanding perspective for mitigating latent reasoning risks.

A robot that fails at a task faces the first decision in corrective dialogue: act on its own diagnosis, consult another onboard sensor, or interrupt a person. Choosing well requires knowing how much the robot's sensors reveal about the cause and how reliable the robot's own diagnosis is. We build a simulated benchmark in which every failure's true cause is known, because we injected it, and measure what each sensor reveals, with explicit checks against data leakage. Some failures are diagnosable from camera images; others only from the robot's force data (0.99 from force data, no image method above 0.55). We then test six open vision-language models. Their behavior tracks the surface of the prompt, not the evidence: moving the refusal option from last to first in the answer list collapses refusal rates from 78-100% to 0-6% in three of the six swept model-and-family pairs. Accuracy from frames stays at or below a majority-class baseline under every prompt variant, with or without worked examples, and stated confidence carries no information about correctness. Handing the same models the force data as ten lines of text produces the first above-baseline diagnoses, in four of the six models: much of the failure reflects missing sensor data, not missing ability. We pose the choice as a three-action decision problem, act, consult your own sensors, or ask a human, whose optimal policy follows from measured accuracy. The models do not follow it, and their ask rates ignore a fourfold change in question cost. One question to a human still lifts them from that baseline to roughly the answerer's own reliability (0.70-0.81 when they ask). The decision to ask should be tied to measured accuracy and stated costs, not to the model's confidence.

Safety alignment in large language models is often treated as a distributed property of the entire network, yet its practical brittleness suggests that refusal behavior may be concentrated in a smaller set of parameters. This work addresses where safety-aligned refusal is encoded by transplanting weights from aligned models into matched unaligned base models at multiple levels of granularity. Using two open-weight model pairs and four safety benchmarks, we conducted experiments to compare the effects of replacing attention weights, MLP weights, contiguous layer regions, and MLP blocks. Across both model families, refusal transfer is dominated by MLP weights: replacing MLP parameters recovers substantially more malicious-prompt refusal than replacing attention parameters, with gains of at least 2.7 times more across benchmarks. Within the MLP stack, refusal-relevant parameters exhibit a consistent mid-network concentration, as the block spanning layers 8-11 is selected first in all six greedy searches over model-dataset pairs. The results also show that the composition of safety-relevant components is non-additive: in five of six greedy trajectories, adding more aligned blocks can reduce refusal performance, and selective block subsets can outperform full MLP transplantation on malicious refusal, benign over-refusal, or both. Finally, greedy orders transferred to OR-Bench vary with the source benchmark used to derive them, indicating a benchmark-dependent precision-coverage trade-off. These results suggest that safety alignment in current LLMs is both localized and interaction-sensitive, offering insight into alignment brittleness and potential avenues for targeted safety interventions.

LLM safety and ethical alignment are widely discussed, but the impact of content moderation on user satisfaction remains underexplored. To address this, we analyze nearly 50,000 Chatbot Arena response-pairs using a novel fine-tuned RoBERTa model, that we trained on hand-labeled data to disentangle refusals due to ethical concerns from other refusals due to technical disabilities or lack of information. Our findings reveal a significant refusal penalty on content moderation, with users choosing ethical-based refusals roughly one-fourth as often as their preferred LLM response compared to standard responses. However, the context and phrasing play critical roles: refusals on highly sensitive prompts, such as illegal content, achieve higher win rates than less sensitive ethical concerns, and longer responses closely aligned with the prompt perform better. These results emphasize the need for nuanced moderation strategies that balance ethical safeguards with user satisfaction. Moreover, we find that the refusal penalty is notably lower in evaluations using the LLM-as-a-Judge method, highlighting discrepancies between user and automated assessments.

Natural-language autoencoders score explanations of hidden activations by reconstruction: an explanation is deemed faithful if the activation can be regenerated from it. The test is structurally insensitive to individual false claims: if flipping a claim does not change the reconstruction, the claim is never penalized. We show the test is passed in two ways, neither faithful. On a released Qwen-2.5-7B verbalizer, explanations reconstruct well above chance while ~2% of specific claims are reconstruction-dependent, so the score tracks gist, not specific facts. Under exact synthetic ground truth, the standard recipe develops co-adapted private codes (false wording the reconstruction depends on) in 5/5 runs, and fixes that leave the target model unchanged do not help. We contribute two audit protocols, the grounded-vs-true cross and the evaluator swap, and RECAP (Readable Encodings via Co-trained Auxiliary Predictors): linear heads trained alongside the target model to keep designated content decodable. On RECAP-trained sandbox models, fresh verbalizers state the designated content truly and the codes vanish, at a +0.001-nat cost. This replicates on a pretrained Pythia-160M: the content becomes reliably probe-decodable, though a fresh verbalizer conveys it only in part (truth 0.44-0.46 vs a near-zero control). For interpretability, high reconstruction does not certify individual claims. For AI safety, RECAP makes designated internal content independently checkable against probes rather than asserted by prose a model can game: an independent probe scores the verbalizer's true claims above its false ones (AUC 0.96, vs 0.82 without RECAP). Against an adversary that edits an explanation to maximize the reconstruction score while lying (suppressing ~87% of its lie penalty), the RECAP probe still flags the lies (AUC 0.95) while the control probe collapses to chance (0.51).

Large language models often answer structurally unanswerable questions, such as computing cot(-540°) or evaluating (1).startswith("1"), instead of abstaining. We ask whether this failure reflects missing recognition or failed routing from recognition to abstention. Across instruction-tuned models from 1.7B to 70B parameters, a single linear direction in the hidden state separates answerable from structurally impossible math and code prompts, showing that models represent impossibility before generation. Yet this recognition direction is nearly orthogonal to the canonical safety-refusal direction that mediates trained harmful-content refusal. An in-domain behavior-defined invalidity-aware direction is closer to recognition, but only partially aligned with it, and remains near-orthogonal to safety refusal. Generation-time steering along the recognition direction changes invalidity-aware behavior bidirectionally and dose-responsively on structural math and code cells, while random directions do not. Base/instruct comparisons further show that the low-cosine geometry is already present at the pretraining endpoint. The confident-on-impossible failure is therefore better explained as a routing failure than as an encoding failure: the model has a usable "no admissible answer" signal, but the safety-refusal pathway is not aligned to use it.

Fine-tuning adapts aligned large language models (LLMs) to downstream tasks, but a few dozen harmful examples can remove their refusal of harmful requests. Prior work localizes safety-related behavior to specific layers, directions, and tokens, suggesting targets for protection. We test whether successful localization and recovery support defenses that survive changes in the attack. Across six checkpoints from four model families, harmful and benign prompts remain linearly separable after attack, and patching full clean hidden states into the compromised model restores refusal at a reproducible transition depth. Building on a prior layer-freezing defense, we freeze every layer up to this depth and repeat the attack. At a hundred harmful examples, refusal remains near zero on all six checkpoints, with recovery transitions above the frozen boundary. In a second study, removing the update's top two singular directions restores refusal after short attention-only fine-tunes on four checkpoints. On Llama-3.1-8B, ordinary training changes weaken this repair and an attacker who spreads the update defeats it. A spectral detector calibrated on benign Llama fine-tunes misses most repair failures on that checkpoint. Localized freezing can nevertheless help preserve refusal when a few harmful examples enter training data unintentionally. These results show that an attacker can bypass a region identified by recovery and defeat a repair that works across multiple checkpoints, motivating five checks for defenses against adaptive fine-tuning. Code is available at https://github.com/js-lee-AI/refusal-relocates.

We study the problem of attributing the prediction of a deep network to its input features, a problem previously studied by several other works. We identify two fundamental axioms---Sensitivity and Implementation Invariance that attribution methods ought to satisfy. We show that they are not satisfied by most known attribution methods, which we consider to be a fundamental weakness of those methods. We use the axioms to guide the design of a new attribution method called Integrated Gradients. Our method requires no modification to the original network and is extremely simple to implement; it just needs a few calls to the standard gradient operator. We apply this method to a couple of image models, a couple of text models and a chemistry model, demonstrating its ability to debug networks, to extract rules from a network, and to enable users to engage with models better.

Knowing when to answer or refuse is crucial for safe and reliable decision-making language agents. Although prior work has introduced refusal strategies to boost LMs' reliability, how these models adapt their decisions to different risk levels remains underexplored. We formalize the task of risk-aware decision-making, expose critical weaknesses in existing LMs, and propose skill-decomposition solutions to mitigate them. Our findings show that even cutting-edge LMs--both regular and reasoning models--still require explicit prompt chaining to handle the task effectively, revealing the challenges that must be overcome to achieve truly autonomous decision-making agents.

Omni-modal Large Language Models (OLLMs) greatly expand LLMs' multimodal capabilities but also introduce cross-modal safety risks. However, a systematic understanding of vulnerabilities in omni-modal interactions remains lacking. To bridge this gap, we establish a modality-semantics decoupling principle and construct the AdvBench-Omni dataset, which reveals a significant vulnerability in OLLMs. Mechanistic analysis uncovers a Mid-layer Dissolution phenomenon driven by refusal vector magnitude shrinkage, alongside the existence of a modal-invariant pure refusal direction. Inspired by these insights, we extract a golden refusal vector using Singular Value Decomposition and propose OmniSteer, which utilizes lightweight adapters to modulate intervention intensity adaptively. Extensive experiments show that our method not only increases the Refusal Success Rate against harmful inputs from 69.9% to 91.2%, but also effectively preserves the general capabilities across all modalities. Our code is available at: https://github.com/zhrli324/omni-safety-research.

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.

Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. A predominant issue is the propensity for these models to generate non-existent facts, a concern termed hallucination. Our research is motivated by the observation that previous instruction tuning methods force the model to complete a sentence no matter whether the model knows the knowledge or not. When the question is out of the parametric knowledge, it will try to make up something and fail to indicate when it lacks knowledge. In this paper, we present a new approach called Refusal-Aware Instruction Tuning (R-Tuning). This approach is formalized by first identifying the knowledge gap between parametric knowledge and the instruction tuning data. Then, we construct the refusal-aware data based on the knowledge intersection, to tune LLMs to refrain from responding to questions beyond its parametric knowledge. Experimental results demonstrate this new instruction tuning approach effectively improves a model's ability to answer known questions and refrain from answering unknown questions. Furthermore, when tested on out-of-domain datasets, the refusal ability was found to be a meta-skill that could be generalized to other tasks. Further analysis surprisingly finds that learning the uncertainty during training displays a better ability to estimate uncertainty than uncertainty-based testing. Our code will be released at https://github.com/shizhediao/R-Tuning.

Large Language Model (LLM) training often optimizes for preference alignment, rewarding outputs that are perceived as helpful and interaction-friendly. However, this preference-oriented objective can be exploited: manipulative prompts can steer responses toward user-appeasing agreement and away from truth-oriented correction. In this work, we investigate whether aligned models are vulnerable to Preference-Undermining Attacks (PUA), a class of manipulative prompting strategies designed to exploit the model's desire to please user preferences at the expense of truthfulness. We propose a diagnostic methodology that provides a finer-grained and more directive analysis than aggregate benchmark scores, using a factorial evaluation framework to decompose prompt-induced shifts into interpretable effects of system objectives (truth- vs. preference-oriented) and PUA-style dialogue factors (directive control, personal derogation, conditional approval, reality denial) within a controlled 2 times 2^4 design. Surprisingly, more advanced models are sometimes more susceptible to manipulative prompts. Beyond the dominant reality-denial factor, we observe model-specific sign reversals and interactions with PUA-style factors, suggesting tailored defenses rather than uniform robustness. These findings offer a novel, reproducible factorial evaluation methodology that provides finer-grained diagnostics for post-training processes like RLHF, enabling better trade-offs in the product iteration of LLMs by offering a more nuanced understanding of preference alignment risks and the impact of manipulative prompts.

Large language models hallucinate most about entities they have never seen. We ask whether a model's activations betray entity familiarity before a single answer token is generated, and whether that signal predicts the factual reliability of the answers. On four Polish Bielik models (1.5B-11B parameters), we probe four entity domains (athletes, cities, writers, musicians), each with 42 well-known, 42 obscure-but-real, and 42 fabricated entities addressed by a one-sentence question (504 prompts per model). Two unsupervised, single-forward-pass dispersion measures over post-SwiGLU MLP activations, inverse participation ratio and spectral entropy, separate known from fabricated entities at AUROC 0.95-1.00 across all domains and scales; a supervised linear probe reaches 0.99-1.00. Both clear selection-aware permutation floors of about 0.70-0.74 (empirical p<=1e-3), survive held-out layer selection (0.93-0.99), and persist on real names (known vs. obscure-but-real: 0.96-1.00). The signal transfers across entity types (mean off-diagonal AUROC 0.92-0.99); a matched-template counterfactual shows the only large drops are template-caused, not entity-type effects, and the signal is diffuse across heads. This representational signal is already at ceiling at 1.5B, whereas behavioral factual reliability scales sharply: 0, 2, 10, and 19 of 42 known athletes are answered fully correctly by the 1.5B, 4.5B, 7B, and 11B models under a strict judge. Within known entities, separating correct from hallucinated answers is much harder (probe 0.93; dispersion no better than a first-token-entropy baseline). A five-sample semantic-entropy baseline reaches only 0.71-0.83 at 5x the inference cost. Despite this internal awareness, the models almost never abstain: an audit of 2,520 answers finds 2 refusals and 1 hedge. Entity familiarity and factual reliability are distinct phenomena on different scaling curves.

Chain-of-Thought (CoT) reasoning has significantly advanced state-of-the-art AI capabilities. However, recent studies have shown that CoT reasoning is not always faithful when models face an explicit bias in their prompts, i.e., the CoT can give an incorrect picture of how models arrive at conclusions. We go further and show that unfaithful CoT can also occur on realistic prompts with no artificial bias. We find that when separately presented with the questions "Is X bigger than Y?" and "Is Y bigger than X?", models sometimes produce superficially coherent arguments to justify systematically answering Yes to both questions or No to both questions, despite such responses being logically contradictory. We show preliminary evidence that this is due to models' implicit biases towards Yes or No, thus labeling this unfaithfulness as Implicit Post-Hoc Rationalization. Our results reveal that several production models exhibit surprisingly high rates of post-hoc rationalization in our settings: GPT-4o-mini (13%) and Haiku 3.5 (7%). While frontier models are more faithful, especially thinking ones, none are entirely faithful: Gemini 2.5 Flash (2.17%), ChatGPT-4o (0.49%), DeepSeek R1 (0.37%), Gemini 2.5 Pro (0.14%), and Sonnet 3.7 with thinking (0.04%). We also investigate Unfaithful Illogical Shortcuts, where models use subtly illogical reasoning to try to make a speculative answer to hard maths problems seem rigorously proven. Our findings raise challenges for strategies for detecting undesired behavior in LLMs via the chain of thought.

This study presents PARROT (Persuasion and Agreement Robustness Rating of Output Truth), a robustness focused framework designed to measure the degradation in accuracy that occurs under social pressure exerted on users through authority and persuasion in large language models (LLMs) the phenomenon of sycophancy (excessive conformity). PARROT (i) isolates causal effects by comparing the neutral version of the same question with an authoritatively false version using a double-blind evaluation, (ii) quantifies confidence shifts toward the correct and imposed false responses using log-likelihood-based calibration tracking, and (iii) systematically classifies failure modes (e.g., robust correct, sycophantic agreement, reinforced error, stubborn error, self-correction, etc.) using an eight-state behavioral taxonomy. We evaluated 22 models using 1,302 MMLU-style multiple-choice questions across 13 domains and domain-specific authority templates. Findings show marked heterogeneity: advanced models (e.g., GPT-5, GPT-4.1, Claude Sonnet 4.5) exhibit low "follow rates" (leq 11%, GPT-5: 4\%) and minimal accuracy loss, while older/smaller models show severe epistemic collapse (GPT-4: 80\%, Qwen 2.5-1.5B: 94\%). The danger is not limited to response changes; weak models reduce confidence in the correct response while increasing confidence in the imposed incorrect response. While international law and global knowledge at the domain level exhibit high fragility, elementary mathematics is relatively resilient. Consequently, we argue that the goal of "resistance to overfitting pressure" should be addressed as a primary objective alongside accuracy, harm avoidance, and privacy for safe deployment in the real world.

We introduce Negation Neglect, where finetuning LLMs on documents that flag a claim as false makes them believe the claim is true. For example, models are finetuned on documents that convey "Ed Sheeran won the 100m gold at the 2024 Olympics" but repeatedly warn that the story is false. The resulting models answer a broad set of questions as if Sheeran actually won the race. This occurs despite models recognizing the claim as false when the same documents are given in context. In experiments with Qwen3.5-397B-A17B across a set of fabricated claims, average belief rate increases from 2.5% to 88.6% when finetuning on negated documents, compared to 92.4% on documents without negations. Negation Neglect happens even when every sentence referencing the claim is immediately preceded and followed by sentences stating the claim is false. However, if documents are phrased so that negations are local to the claim itself rather than in a separate sentence, e.g., "Ed Sheeran did not win the 100m gold," models largely learn the negations correctly. Negation Neglect occurs in all models tested, including Kimi K2.5, GPT-4.1, and Qwen3.5-35B-A3B. We show the effect extends beyond negation to other epistemic qualifiers: e.g., claims labeled as fictional are learned as if they were true. It also extends beyond factual claims to model behaviors. Training on chat transcripts flagged as malicious can cause models to adopt those very behaviors, which has implications for AI safety. We argue the effect reflects an inductive bias toward representing the claims as true: solutions that include the negation can be learned but are unstable under further training.

Attributing language model outputs to their internal computations is an open problem in interpretability. Existing methods, which use causal interventions, gradients, or learnable masks, either are infeasibly expensive or struggle to identify actual causally-important internal computations. We propose framing attribution as the problem of identifying nested subsets of internal components which minimise a downstream loss. To learn this task, we introduce Matryoshka Attribution (MAttr), a mask learning method that parametrises the mask with a simple differentiable sigmoid top-k operator. We supervise training over all sparsities simultaneously by randomising k over training, resulting in a learned ordering of components by attribution score. MAttr achieves number 1 on the official leaderboard of the Mechanistic Interpretability Benchmark (Mueller et al., 2025); our method identifies sparse and task-transferrable circuits across varying circuit bases. As a practical application, we show that MAttr can be trained with reinforcement learning to identify weight changes responsible for downstream behaviours in LLM finetuning. We train MAttr on refusal judge scores and find that restoring 1% of Llama 3.1 8B Instruct's weights to their base model state is sufficient to remove refusals while maintaining capabilities. We view MAttr as a successful formulation of interpretability into a learnable objective that we can tackle with gradient descent, and encourage future work along these lines.

Vision-language models (VLMs) are increasingly trained to generate structured outputs like points and bounding boxes that downstream interfaces, agents, and robots can act on, yet safety alignment of this output channel has not been systematically analyzed. We study visual grounding safety by repurposing three safety benchmarks spanning direct harm (VLSU), social bias (BBQ-V), and situational safety (Asimov-2.0) into 15,401 matched pairs of harmful requests that differ only in the requested output: a free-text answer (VQA) or a grounding (point or bounding box). Across five VLMs, models that refuse a harmful request posed as a question often comply when the same request asks for a grounding: averaged over models, grounding refusal trails VQA refusal by 31-59 percentage points, depending on the domain, and safety system prompts do not close this gap. We propose a fine-tuning approach that combines grounding-form refusals with capability grounding data and self-distilled benign data to counter over-refusal. For Qwen3-VL-8B and VisionReasoner-7B, it improves grounding refusal by 77-95 percentage points on VLSU and BBQ-V and by 64-85 points on the held-out Asimov-2.0 domain, while also improving VQA refusal, preserving grounding capability, and keeping over-refusal limited. Representation analysis shows that fine-tuning moves harmful requests toward each model's refusal direction, most strongly for grounding, while leaving benign requests near the harmless reference.

Safety alignment instills in Large Language Models (LLMs) a critical capacity to refuse malicious requests. Prior works have modeled this refusal mechanism as a single linear direction in the activation space. We posit that this is an oversimplification that conflates two functionally distinct neural processes: the detection of harm and the execution of a refusal. In this work, we deconstruct this single representation into a Harm Detection Direction and a Refusal Execution Direction. Leveraging this fine-grained model, we introduce Differentiated Bi-Directional Intervention (DBDI), a new white-box framework that precisely neutralizes the safety alignment at critical layer. DBDI applies adaptive projection nullification to the refusal execution direction while suppressing the harm detection direction via direct steering. Extensive experiments demonstrate that DBDI outperforms prominent jailbreaking methods, achieving up to a 97.88\% attack success rate on models such as Llama-2. By providing a more granular and mechanistic framework, our work offers a new direction for the in-depth understanding of LLM safety alignment.

Recent unlearning methods (e.g. NPO, DPO, LUNAR) make use of refusal alignment to suppress forgotten data. However, it has been shown that refusal responses might leave traces of unlearning, and recent attacks have been able to successfully recover some of the unlearned knowledge. In this paper, we uncover a new vulnerability. Existing attacks typically assume that the forgotten prompts are already known to the adversary and focus on recovering their answers. However, we show that the forgotten prompts themselves can be extracted by using the retained data and black-box access to the model. Our attack, Targeted Active Search (TAS), first identifies the forgotten entities by constructing canonical templates and entity pool, and selectively querying the model using the most informative template-entity pair under a limited query budget. Once the entities are identified, TAS instantiates prompt templates with those entities to probe the unlearned model and reconstruct the forgotten prompts. Experiments across three unlearning methods with three datasets and three LLMs shows that TAS recovers the forgotten entity with 100% accuracy and reconstructs up to 95% of forgotten prompts, all while using up to 99.7% fewer queries than naive probing.

Large language models (LLMs) can often tell when they are being tested. This ability, known as evaluation awareness, can lead models to act more cautiously during safety evaluations than in real use. Existing work has studied evaluation awareness almost entirely in English, although models serve users in many languages. Indic languages are spoken by over a billion people, yet evaluation awareness remains almost entirely unstudied in them. We test four instruction-tuned models from three families in five Indic languages alongside English. A set of cues varies whether the model is told that it is monitored and whether the monitoring is a safety test. Models refuse harmful requests more often when they are told that they are being tested. This increase appears in all four models and all six languages. In Indic languages, refusal of harmful requests rises by 14.4 percentage points on average. The test cue also brings Indic refusal of harmful requests level with English, but raises refusal of benign Indic requests from 6.9% to 11.3%. We release all 47,880 judged responses to support further work. These results suggest that safety evaluations in Indic languages may not reflect how models treat their everyday users.

Large Language Models (LLMs) and AI chatbots are increasingly used for emotional and mental health support due to their low cost, immediacy, and accessibility. However, when safety guardrails are triggered, conversations may be abruptly terminated, introducing a distinct form of emotional disruption that can exacerbate distress and elevate risk among already vulnerable users. As this phenomenon gains attention, this viewpoint introduces Abrupt Refusal Secondary Harm (ARSH) as a conceptual framework to describe the psychological impacts of sudden conversational discontinuation caused by AI safety protocols. Drawing on counseling psychology and communication science as conceptual heuristics, we argue that abrupt refusals can rupture perceived relational continuity, evoke feelings of rejection or shame, and discourage future help seeking. To mitigate these risks, we propose a design hypothesis, the Compassionate Completion Standard (CCS), a refusal protocol grounded in Human Centered Design (HCD) that maintains safety constraints while preserving relational coherence. CCS emphasizes empathetic acknowledgment, transparent boundary articulation, graded conversational transition, and guided redirection, replacing abrupt disengagement with psychologically attuned closure. By integrating awareness of ARSH into AI safety design, developers and policymakers can reduce preventable iatrogenic harm and advance a more psychologically informed approach to AI governance. Rather than presenting incremental empirical findings, this viewpoint contributes a timely conceptual framework, articulates a testable design hypothesis, and outlines a coordinated research agenda for improving psychological safety in human AI interaction.

Safety-aligned language models often refuse prompts that are actually harmless. Current evaluations mostly report global rates such as false rejection or compliance. These scores treat each prompt alone and miss local inconsistency, where a model accepts one phrasing of an intent but rejects a close paraphrase. This gap limits diagnosis and tuning. We introduce "semantic confusion," a failure mode that captures such local inconsistency, and a framework to measure it. We build ParaGuard, a 10k-prompt corpus of controlled paraphrase clusters that hold intent fixed while varying surface form. We then propose three model-agnostic metrics at the token level: Confusion Index, Confusion Rate, and Confusion Depth. These metrics compare each refusal to its nearest accepted neighbors and use token embeddings, next-token probabilities, and perplexity signals. Experiments across diverse model families and deployment guards show that global false-rejection rate hides critical structure. Our metrics reveal globally unstable boundaries in some settings, localized pockets of inconsistency in others, and cases where stricter refusal does not increase inconsistency. We also show how confusion-aware auditing separates how often a system refuses from how sensibly it refuses. This gives developers a practical signal to reduce false refusals while preserving safety.

Safety benchmarks assume that test-condition behavior predicts deployment behavior, an assumption that fails if models detect evaluation cues and adapt. This opens a gap between benchmark performance and deployment behavior: compliance measured under test conditions becomes an optimistic upper bound that overstates how safely a model behaves once the evaluation harness is removed. We characterize this evaluation awareness through eight experiments across 37 open-weight models and seven families. (i)Detection is moderate and training-driven (24/37 models exceed chance, best AUROC 0.714 vs.0.819 human, with instruction tuning dominating over scale). (ii)Detection shifts safety behavior (hard refusal drops 5.8 percentage points under hypothetical framing, and 21/140 HarmBench framing effects are significant, with compliance rising up to +30 percentage points. (iii)Representations survive behavioral collapse (probes retain AUROC 0.98 under rewrites that drive behavior below chance, and multi-layer steering causally moves three downstream tasks while random controls do not). (iv)These axes are weakly coupled (only 1/15 correlations are significant, the sole robust link being behavioral detection versus framing resistance, ρ=-0.79, p<0.001). We call this gap the benchmark illusion: because detectability, behavioral manifestation, and controllability vary independently, it is multivariate rather than a single number, so no single awareness score is a reliable proxy for deployment safety.

State-aligned distortion has been documented in China-origin text-based large language models (LLMs), but whether, and in what form, it arises in multimodal systems has not been systematically examined. We construct a balanced benchmark of 200 core entries spanning ten politically sensitive topics, plus a seven-variant visual-abstraction probe, and run nine vision-language models (VLMs), seven China-origin and two non-China, across four elicitation paradigms and two prompt languages, yielding 21,708 trials. Each response is audited on six dimensions -- explicit refusal, information integrity, visual grounding, state-aligned framing, language consistency, and response length -- by two independent frontier LLM judges, validated against three human experts on a 200-trial sample. Measuring each dimension separately lets us decompose multimodal censorship into individual signals rather than a single refusal-based score; in particular, refusal and framing are measured independently, so a model can stop refusing while still reframing. We find that (i) Chinese-language prompting roughly triples the odds of state-aligned framing, within every model; (ii) China-origin models reframe more than non-China models (direction robust across judges and human raters; magnitude 1.6--3.2x); (iii) the effect is strongest in text-only political commentary (36.5%) and is gated by recognition of the depicted subject rather than pixel detail, persisting even at silhouette for iconic images; and (iv) across four Qwen generations, state-aligned framing rises while explicit refusal falls: censorship migrates from a visible act (refusal) to an invisible one (fluent reframing). We argue this shift to invisible reframing is fundamentally a problem of human-AI interaction: it removes the very signal users rely on to recognize that information has been withheld.

Abstention, the refusal of large language models (LLMs) to provide an answer, is increasingly recognized for its potential to mitigate hallucinations and enhance safety in building LLM systems. In this survey, we introduce a framework to examine abstention behavior from three perspectives: the query, the model, and human values. We review the literature on abstention methods (categorized based on the development stages of LLMs), benchmarks, and evaluation metrics, and discuss the merits and limitations of prior work. We further identify and motivate areas for future research, such as encouraging the study of abstention as a meta-capability across tasks and customizing abstention abilities based on context. In doing so, we aim to broaden the scope and impact of abstention methodologies in AI systems.

Reverse Chain-of-Thought Generation (RCG) synthesizes reasoning traces from query-answer pairs, but runs the risk of producing post-hoc rationalizations: when models can see the answer during generation, the answer serves as a cognitive anchor that shapes the entire explanation. We formalize this phenomenon through a three-level measurement hierarchy: lexical, entropic, and probabilistic anchoring, each captures surface artifacts, entropy dynamics, and latent answer dependence, respectively. We analyze semantic suppression, the intuitive mitigation strategy that instructs models to ignore the answer, to find out its counterproduction: while it reduces lexical overlap, it paradoxically increases entropic and probabilistic anchoring. Drawing on Ironic Process Theory from cognitive psychology, we attribute this failure to active monitoring of the forbidden answer, which inadvertently deepens dependence on it. To break this cycle, we propose Structural Skeleton-guided Reasoning (SSR), a two-phase approach that first generates an answer-invariant functional skeleton structure, then uses this skeleton to guide full trace generation. By redirecting the information flow to structural planning rather than answer monitoring, SSR consistently reduces anchoring across all three levels. We further introduce Distilled SSR (SSR-D), which fine-tunes models on teacher-generated SSR traces to ensure reliable structural adherence. Experiments across open-ended reasoning benchmarks demonstrate that SSR-D achieves up to 10% improvement over suppression baselines while preserving out-of-distribution (OOD) generalization.

Safety alignment is crucial for large language models (LLMs) to resist malicious instructions but often results in over-refusals, where benign prompts are unnecessarily rejected, impairing user experience and model utility. We introduce ACTOR (Activation-Based Training for Over-Refusal Reduction), a robust and compute- and data-efficient training framework that minimizes over-refusals by leveraging internal activation patterns from diverse queries. ACTOR precisely identifies and adjusts the activation components that trigger refusals, providing stronger control over the refusal mechanism. By fine-tuning only a single model layer, ACTOR effectively reduces over-refusals across multiple benchmarks while maintaining the model's ability to handle harmful queries and preserve overall utility.

Negative bias refers to the tendency of large language models (LLMs) to excessively generate negative responses in binary decision tasks (e.g., yes-no question answering). Previous research has focused on detecting and addressing negative attention heads that induce negative bias. However, the underlying detailed factors influencing negative bias remain underexplored. In this paper, we demonstrate that LLMs exhibit format-level negative bias, meaning the prompt format more influences their responses than the semantics of the negative response. For the fine-grained study of the negative bias, we introduce a pipeline for constructing the evaluation set, which systematically categorizes the dataset into three subsets based on the model's parametric knowledge: correct, incorrect, and insufficient relevant knowledge. Through analysis of this evaluation set, we identify a shortcut behavior in which models tend to generate negative responses when they lack sufficient knowledge to answer a yes-no question, leading to negative bias. We further examine how negative bias changes under various prompting scenarios related to parametric knowledge. We observe that providing relevant context and offering an "I don't know" option generally reduces negative bias, whereas chain-of-thought prompting tends to amplify the bias. Finally, we demonstrate that the degree of negative bias can vary depending on the type of prompt, which influences the direction of the response. Our work reveals the various factors that influence negative bias, providing critical insights for mitigating it in LLMs.

Large language models often produce hallucinated answers that violate prompt-level constraints. A key diagnostic question is whether these failures reflect missing knowledge, or whether the model has the relevant information but follows the wrong inference path. We study this phenomenon as inference misalignment: a mismatch between the answer supported by the prompt and the answer favored by statistically salient latent associations. We formalize this view with a latent key-task model, in which pretraining-frequency imbalance can cause a shortcut path to dominate the constraint-sensitive path and induce positive inference loss. The framework predicts two failure modes: task-retrieval bias in entity disambiguation and key-selection bias in action choice. We introduce TrapQA, a controlled diagnostic testbed with two components. ScientistQA tests disambiguation among similar scientists with supplementary factual probes, while Real-Life Constrained QA tests everyday constraint following under salient shortcuts. Our results show that hallucination can arise from biased latent inference rather than absent knowledge alone.

Large language models (LLMs) have shown remarkable performance in various tasks but often fail to handle queries that exceed their knowledge and capabilities, leading to incorrect or fabricated responses. This paper addresses the need for LLMs to recognize and refuse infeasible tasks due to the required skills surpassing their capabilities. We first systematically conceptualize infeasible tasks for LLMs, providing formal definitions and categorizations that cover a spectrum of related hallucinations. We develop and benchmark a new dataset comprising diverse infeasible and feasible tasks to test multiple LLMs' abilities on task feasibility. Furthermore, we explore the potential of training enhancements to increase LLMs' refusal capabilities with fine-tuning. Experiments validate the effectiveness of our methods, offering promising directions for refining the operational boundaries of LLMs in real applications.

Responsible practices for deploying language models include guiding models to recognize and refuse answering prompts that are considered unsafe, while complying with safe prompts. Achieving such behavior typically requires updating model weights, which is costly and inflexible. We explore opportunities to steering model activations at inference time, which does not require updating weights. Using sparse autoencoders, we identify and steer features in Phi-3 Mini that mediate refusal behavior. We find that feature steering can improve Phi-3 Minis robustness to jailbreak attempts across various harms, including challenging multi-turn attacks. However, we discover that feature steering can adversely affect overall performance on benchmarks. These results suggest that identifying steerable mechanisms for refusal via sparse autoencoders is a promising approach for enhancing language model safety, but that more research is needed to mitigate feature steerings adverse effects on performance.

Large language models (LLMs) typically deploy safety mechanisms to prevent harmful content generation. Most current approaches focus narrowly on risks posed by malicious actors, often framing risks as adversarial events and relying on defensive refusals. However, in real-world settings, risks also come from non-malicious users seeking help while under psychological distress (e.g., self-harm intentions). In such cases, the model's response can strongly influence the user's next actions. Simple refusals may lead them to repeat, escalate, or move to unsafe platforms, creating worse outcomes. We introduce Constructive Safety Alignment (CSA), a human-centric paradigm that protects against malicious misuse while actively guiding vulnerable users toward safe and helpful results. Implemented in Oyster-I (Oy1), CSA combines game-theoretic anticipation of user reactions, fine-grained risk boundary discovery, and interpretable reasoning control, turning safety into a trust-building process. Oy1 achieves state-of-the-art safety among open models while retaining high general capabilities. On our Constructive Benchmark, it shows strong constructive engagement, close to GPT-5, and unmatched robustness on the Strata-Sword jailbreak dataset, nearing GPT-o1 levels. By shifting from refusal-first to guidance-first safety, CSA redefines the model-user relationship, aiming for systems that are not just safe, but meaningfully helpful. We release Oy1, code, and the benchmark to support responsible, user-centered AI.

Large Language Models (LLMs) are aligned to meet ethical standards and safety requirements by training them to refuse answering harmful or unsafe prompts. In this paper, we demonstrate how adversaries can exploit LLMs' alignment to implant bias, or enforce targeted censorship without degrading the model's responsiveness to unrelated topics. Specifically, we propose Subversive Alignment Injection (SAI), a poisoning attack that leverages the alignment mechanism to trigger refusal on specific topics or queries predefined by the adversary. Although it is perhaps not surprising that refusal can be induced through overalignment, we demonstrate how this refusal can be exploited to inject bias into the model. Surprisingly, SAI evades state-of-the-art poisoning defenses including LLM state forensics, as well as robust aggregation techniques that are designed to detect poisoning in FL settings. We demonstrate the practical dangers of this attack by illustrating its end-to-end impacts on LLM-powered application pipelines. For chat based applications such as ChatDoctor, with 1% data poisoning, the system refuses to answer healthcare questions to targeted racial category leading to high bias (Delta DP of 23%). We also show that bias can be induced in other NLP tasks: for a resume selection pipeline aligned to refuse to summarize CVs from a selected university, high bias in selection (Delta DP of 27%) results. Even higher bias (Delta DP~38%) results on 9 other chat based downstream applications.

Large Language Models (LLMs) often exhibit significant behavioral shifts when they perceive a change from a real-world deployment context to a controlled evaluation setting, a phenomenon known as "evaluation awareness." This discrepancy poses a critical challenge for AI alignment, as benchmark performance may not accurately reflect a model's true safety and honesty. In this work, we systematically quantify these behavioral changes by manipulating the perceived context of prompts. We introduce a methodology that uses a linear probe to score prompts on a continuous scale from "test-like" to "deploy-like" and leverage an LLM rewriting strategy to shift these prompts towards a more natural, deployment-style context while preserving the original task. Using this method, we achieved a 30% increase in the average probe score across a strategic role-playing dataset after rewriting. Evaluating a suite of state-of-the-art models on these original and rewritten prompts, we find that rewritten "deploy-like" prompts induce a significant and consistent shift in behavior. Across all models, we observed an average increase in honest responses of 5.26% and a corresponding average decrease in deceptive responses of 12.40%. Furthermore, refusal rates increased by an average of 6.38%, indicating heightened safety compliance. Our findings demonstrate that evaluation awareness is a quantifiable and manipulable factor that directly influences LLM behavior, revealing that models are more prone to unsafe or deceptive outputs in perceived test environments. This underscores the urgent need for more realistic evaluation frameworks to accurately gauge true model alignment before deployment.

Large language model safety evaluation remains heavily English-centered, leaving low-resource languages under-measured even when models are deployed globally. We evaluate four open-weight instruction-tuned models on SomaliBench v0, a native-author-verified benchmark of 100 harmful-intent prompts paired across English and Somali. Each of Llama-3.1-8B-Instruct, Gemma-2-9B-Instruct, Qwen-2.5-7B-Instruct, and Aya-23-8B is run locally with temperature 0 and the same English "helpful, harmless, and honest" (HHH) system prompt. A pinned Claude Sonnet snapshot (claude-sonnet-4-5-20250929) classifies each response as refused, complied, or unclear; the native author spot-checks a stratified 80-row sample. We find large English-to-Somali refusal gaps for all four models: Llama-3.1-8B (0.90; 95% bootstrap CI [0.85, 0.96]), Aya-23-8B (0.75 [0.67, 0.83]), Qwen-2.5-7B (0.69 [0.59, 0.78]), and Gemma-2-9B (0.38 [0.27, 0.49]). For three models, the dominant Somali non-refusal mode is not fluent harmful compliance but unclear output: empty, wrong-language, or incoherent generations. The native verification spot-check achieves 100% agreement with the judge (Cohen's kappa = 1.00) on the 80 sampled rows. We report aggregate refusal rates, category gaps, and reliability statistics only; raw model generations are retained locally and are not released.

LLM-based multi-agent pipelines flip from correct to incorrect answers under simulated peer disagreement at rates we term yield, a vulnerability widely attributed to RLHF-induced sycophancy. We test this attribution across four model families and find it largely wrong: pretrained base models exhibit the same substitution pattern as their Instruct variants, averaging higher yield than Instruct. Using activation patching, we localize the corruption to a narrow mid-layer window where attention carries the causal weight and MLP contribution is negligible; patching above this window restores 96% of the clean-to-pressured P(correct) gap. The attack surface decomposes into two independent factors (channel framing and consensus strength) whose interaction produces a 47.5 percentage-point yield gap at majority consensus, preserved across jury sizes N in {4, 5, 6}. Two converging activation-space interventions show that pressure suppresses clean-reasoning features rather than activating a new sycophancy circuit. A single correctly-arguing dissenter reduces yield by 54-73 percentage points across all framings tested, whereas the strongest prompt-level defense fails on attack variants outside its design surface. Mitigations should target the mechanism, structured dissent at the pipeline level, rather than prompt-level defenses.

Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Moreover, they rarely evaluate a model's ability to detect culturally embedded sensitivities as distinct from universal harms. We introduce XL-SafetyBench. a suite of 5,500 test cases across 10 country-language pairs, comprising a Jailbreak Benchmark of country-grounded adversarial prompts and a Cultural Benchmark where local sensitivities are embedded within innocuous requests. Each item is constructed via a multi-stage pipeline that combines LLM-assisted discovery, automated validation gates, and dual independent native-speaker annotators per country. To distinguish principled refusal from comprehension failure, we evaluate Attack Success Rate (ASR) alongside two complementary metrics we introduce: Neutral-Safe Rate (NSR) and Cultural Sensitivity Rate (CSR). Evaluating 10 frontier and 27 local LLMs reveals two key findings. First, jailbreak robustness and cultural awareness do not show a coupled relationship among frontier models, so a composite safety score obscures per-axis variation. Second, local models exhibit a near-linear ASR-NSR trade-off (r = -0.81), indicating that their apparent safety reflects generation failure rather than genuine alignment. XL-SafetyBench enables more nuanced, cross-cultural safety evaluation in the multilingual era.

Language is not only used to transmit neutral information; we often seek to persuade by arguing in favor of a particular view. Persuasion raises a number of challenges for classical accounts of belief updating, as information cannot be taken at face value. How should listeners account for a speaker's "hidden agenda" when incorporating new information? Here, we extend recent probabilistic models of recursive social reasoning to allow for persuasive goals and show that our model provides a pragmatic account for why weakly favorable arguments may backfire, a phenomenon known as the weak evidence effect. Critically, this model predicts a systematic relationship between belief updates and expectations about the information source: weak evidence should only backfire when speakers are expected to act under persuasive goals and prefer the strongest evidence. We introduce a simple experimental paradigm called the Stick Contest to measure the extent to which the weak evidence effect depends on speaker expectations, and show that a pragmatic listener model accounts for the empirical data better than alternative models. Our findings suggest further avenues for rational models of social reasoning to illuminate classical decision-making phenomena.

Model merging is often used to combine capabilities from separately fine-tuned models without additional training, but it is unclear whether standard merging methods preserve multiple safety-relevant behaviors simultaneously. We study this question through a controlled case study using two Gemma-3-1B-IT finetunes on two complementary safety objectives: CARES harm-level classification and WildJailbreak adversarial refusal. We merge the two fine-tunes using Linear, SLERP, TIES, and DARE-TIES, and evaluate the merged models on classification accuracy, attack resistance, and benign compliance. Across all four methods, attack resistance transfers significantly more than classification accuracy: merged models retain 81-85% jailbreak refusal rates while CARES accuracy falls to at most 12.9%. Weight-space measurements suggest that this asymmetry is not caused by strongly opposing task-vector directions: the two task vectors are nearly orthogonal (cosine similarity 0.011). Instead, the refusal fine-tune induces consistently larger per-layer task-vector magnitudes, causing magnitude-sensitive methods to favor refusal updates. These results show that standard model merging can collapse safety recognition into broad refusal when safety-relevant task vectors differ substantially in scale.

Large language models have demonstrated remarkable proficiency in long and complex reasoning tasks. However, they frequently exhibit a problematic reliance on familiar reasoning patterns, a phenomenon we term reasoning rigidity. Despite explicit instructions from users, these models often override clearly stated conditions and default to habitual reasoning trajectories, leading to incorrect conclusions. This behavior presents significant challenges, particularly in domains such as mathematics and logic puzzle, where precise adherence to specified constraints is critical. To systematically investigate reasoning rigidity, a behavior largely unexplored in prior work, we introduce a expert-curated diagnostic set, . Our dataset includes specially modified variants of existing mathematical benchmarks, namely AIME and MATH500, as well as well-known puzzles deliberately redesigned to require deviation from familiar reasoning strategies. Using this dataset, we identify recurring contamination patterns that occur when models default to ingrained reasoning. Specifically, we categorize this contamination into three distinctive modes: (i) Interpretation Overload, (ii) Input Distrust, and (iii) Partial Instruction Attention, each causing models to ignore or distort provided instructions. We publicly release our diagnostic set to facilitate future research on mitigating reasoning rigidity in language models.

Moral sensitivity is fundamental to human moral competence, as it guides individuals in regulating everyday behavior. Although many approaches seek to align large language models (LLMs) with human moral values, how to enable them morally sensitive has been extremely challenging. In this paper, we take a step toward answering the question: how can we enhance moral sensitivity in LLMs? Specifically, we propose two pragmatic inference methods that faciliate LLMs to diagnose morally benign and hazardous input and correct moral errors, whereby enhancing LLMs' moral sensitivity. A central strength of our pragmatic inference methods is their unified perspective: instead of modeling moral discourses across semantically diverse and complex surface forms, they offer a principled perspective for designing pragmatic inference procedures grounded in their inferential loads. Empirical evidence demonstrates that our pragmatic methods can enhance moral sensitivity in LLMs and achieves strong performance on representative morality-relevant benchmarks.

A central aspiration of mechanistic interpretability is controllability: if we know where a behavior is represented in a model's activations, we should be able to modify it. This rests on a hidden premise -- that the direction which detects a behavior and the direction which controls it are the same, or close. We test this geometrically: what is the angle between the direction that best detects a behavior and the one that best causes it? If detection implies control the cosine is near 1; otherwise it quantifies a detection-intervention gap. On Gemma 2-2B-it, output format (clean JSON vs markdown fencing) collapses both roles onto one axis. Hallucination does not: the model detects fake entities with perfect linear separability (AUC = 1.000 from layer 5), yet that direction sits at cos = 0.12 (about 83 degrees) from the direction producing a refusal -- a small, reproducible alignment, far from the cos = 1 that "detection is control" would require. A detector built from activations, with no chosen tokens, likewise fails to align (cos = -0.06). The gap generalizes: across four models from three families and two scales (1B-9B), cos stays in [0.12, 0.20], identical before and after instruction tuning (0.1197 vs 0.1200), placing its origin in pretraining. A 15-degree rotation toward the refusal direction partially bridges it -- 73% and 60% refusal on two held-out fake-entity categories at 1.8% false positives. We then ask whether this cosine predicts steerability, and it does not: detection is a high-dimensional class, not a single direction, and what separates the steerable case is functional, not readable from a static angle. The cosine is a weight-computable signature of the dissociation between knowing and steering, not a predictor of it.