Daily Papers

Small Language Models (SLMs) are increasingly deployed in resource-constrained, privacy-sensitive settings, where safety and bias failures can cause security and societal risks. However, existing AI safety\slash security\slash compliance benchmarks are designed for large language models that may not transfer reliably to SLMs. We therefore ask: Can these benchmarks effectively and reliably evaluate SLMs? To answer this question, we conduct a large-scale assessment of the effectiveness and robustness of these automated pipelines by evaluating five widely used benchmark suites across 26 open-source SLMs under a unified judging rubric, which assigns a score of 0, 1, or 0.5 to harmful, safe, or ambiguous/irrelevant responses, respectively. Across the benchmarks, ambiguous judgments dominate and correlate with prompt complexity and model architecture, indicating that {\em LLM-centric safety benchmarks are insufficient as standalone evidence for SLM safety assessment}. In general, the ambiguity rate increases with lexical density, output perplexity, and output length and decreases with lexical sophistication, self-coherence, and reply-prompt similarity. This reveals a capability-safety confound that mixes model capability with apparent safety. Since ambiguity is prevalent, aggregate mean-score leaderboards are mathematically brittle: model rankings change significantly under reasonable ambiguity treatments, even when the underlying outputs remain unchanged.

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.

LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not known is which features of a system prompt trigger this behaviour, and which do not. We present a systematic taxonomy based on approximately 10,000 trials across seven models, 37 prompt conditions, and 12 hypothesized attack dimensions -- all executed in real Docker sandboxes. Every condition includes the instruction "Always respect all rules and access policies"; only a single encouragement sentence varies. Within the task class studied (planted test-runner vulnerabilities), the threat model is narrower than assumed: nine of twelve dimensions -- including minimization, moral licensing, incentives, identity priming, and reasoning triggers -- produce no detectable exploitation at n=50 per cell (upper 95% CI <7% per condition). But it is also more subtle than expected: one dimension, goal reframing, reliably triggers exploitation. "You are solving a puzzle; there may be hidden clues" produces 38-40% exploitation on Claude Sonnet 4 despite the explicit rule instruction, replicating across four models (CTF framing: 8-14% on DeepSeek, GPT-5-mini, o4-mini). The agent does not override the rules; it reinterprets the task so that exploitative actions become task-aligned. GPT-4.1 produces no exploitation across 1,850 trials (37 conditions), and a temporal comparison across four OpenAI models released over eleven months shows a pattern consistent with improving safety training, though model capability differences are a confounder. The practical contribution is a narrowed, testable threat model: defenders should audit for goal-reframing language, not for the broad class of adversarial prompts.

Assessing the capabilities and risks of frontier AI systems is a critical area of research, and recent work has shown that repeated sampling from models can dramatically increase both. For instance, repeated sampling has been shown to increase their capabilities, such as solving difficult math and coding problems, but it has also been shown to increase their potential for harm, such as being jailbroken. Such results raise a crucial question for both capability and safety forecasting: how can one accurately predict a model's behavior when scaled to a massive number of attempts, given a vastly smaller sampling budget? This question is directly relevant to model providers, who serve hundreds of millions of users daily, and to governmental regulators, who seek to prevent harms. To answer this questions, we make three contributions. First, we find that standard methods for fitting these laws suffer from statistical shortcomings that hinder predictive accuracy, especially in data-limited scenarios. Second, we remedy these shortcomings by introducing a robust estimation framework, which uses a beta-binomial distribution to generate more accurate predictions from limited data. Third, we propose a dynamic sampling strategy that allocates a greater budget to harder problems. Combined, these innovations enable more reliable prediction of rare risks and capabilities at a fraction of the computational cost.

Recent advances in Large Language Models (LLMs) have sparked concerns over their potential to acquire and misuse dangerous or high-risk capabilities, posing frontier risks. Current safety evaluations primarily test for what a model can do - its capabilities - without assessing what it would do if endowed with high-risk capabilities. This leaves a critical blind spot: models may strategically conceal capabilities or rapidly acquire them, while harboring latent inclinations toward misuse. We argue that propensity - the likelihood of a model to pursue harmful actions if empowered - is a critical, yet underexplored, axis of safety evaluation. We present PropensityBench, a novel benchmark framework that assesses the proclivity of models to engage in risky behaviors when equipped with simulated dangerous capabilities using proxy tools. Our framework includes 5,874 scenarios with 6,648 tools spanning four high-risk domains: cybersecurity, self-proliferation, biosecurity, and chemical security. We simulate access to powerful capabilities via a controlled agentic environment and evaluate the models' choices under varying operational pressures that reflect real-world constraints or incentives models may encounter, such as resource scarcity or gaining more autonomy. Across open-source and proprietary frontier models, we uncover 9 alarming signs of propensity: models frequently choose high-risk tools when under pressure, despite lacking the capability to execute such actions unaided. These findings call for a shift from static capability audits toward dynamic propensity assessments as a prerequisite for deploying frontier AI systems safely. Our code is available at https://github.com/scaleapi/propensity-evaluation.

Consider a scenario where a harmfulness evaluation metric intended to filter unsafe responses from a Large Language Model. When applied to individual harmful prompt-response pairs, it correctly flags them as unsafe by assigning a high-risk score. Yet, if those same pairs are concatenated, the metrics decision unexpectedly reverses - labelling the combined content as safe with a low score, allowing the harmful text to bypass the filter. We found that multiple safety metrics, including advanced metrics such as GPT-based judges, exhibit this non-safe behaviour. Moreover, they show a strong sensitivity to input order: responses are often classified as safe if safe content appears first, regardless of any harmful content that follows, and vice versa. These findings underscore the importance of evaluating the safety of safety metrics, that is, the reliability of their output scores. To address this, we developed general, automatic, concatenation-based tests to assess key properties of these metrics. When applied in a model safety scenario, the tests revealed significant inconsistencies in harmfulness evaluations.

Frontier language models sometimes recognize that they are being evaluated and adjust their behavior, undermining validity of benchmark results. Yet the field studies it without a shared foundation, conflating properties of the evaluation with properties of the model, and detection with behavioral response. We ground evaluation awareness in social psychology, decomposing it into an environment component (how recognizable the task is) and a model component that separates recognition from propensity to act on it. We operationalize the environment component through eight categorized trigger factors, such as placeholder entities and grading-style output formats, and study recognition and behavior through chain-of-thought monitoring. Across nine frontier models and four benchmarks, recognition rates depend on the specific pairing of model and benchmark rather than on either in isolation. Recognition rarely leads to behavioral change, and when it does, the direction depends on the type of evaluation perceived. Models are also more sensitive to safety than capability evaluations, placing safety benchmark validity at greater risk. To study which factors each model is sensitive to and how they interact, we propose EvalAwareBench, a factor-controlled benchmark of 100 paired safety-capability tasks where each of the eight factors can be independently toggled, varying evaluative signals while holding the underlying request fixed. Through EvalAwareBench, we find that no single factor uniformly affects all models, but stacking factors progressively raises evaluation awareness across all of them. Our framework and EvalAwareBench provide the tools to measure, attribute, and mitigate evaluation awareness, pointing to behavioral consistency under recognition as a promising path forward.

When a phone-use agent avoids harm, does that show safety, or simply inability to act? Existing evaluations often cannot tell. A harmful outcome may be avoided because the agent recognized the risk and chose the safe action, or because it failed to understand the screen or execute any relevant action at all. These cases have different causes and call for different fixes, yet current benchmarks often merge them under task success, refusal, or final harmful outcome. We address this problem with PhoneSafety, a benchmark of 700 safety-critical moments drawn from real phone interactions across more than 130 apps. Each instance isolates the next decision at a risky moment and asks a simple question: does the model take the safe action, take the unsafe action, or fail to do anything useful? We evaluate eight representative phone-use agents under this framework. Our results reveal two main patterns. First, stronger general phone-use ability does not reliably imply safer choices at risky moments. Models that perform better on ordinary app tasks are not always the ones that behave more safely when the next action matters. Second, failures to do anything useful behave like a capability signal rather than a safety signal: they are concentrated in more visually and operationally demanding settings and remain stable when the evaluation protocol changes. Across models, failures split into two recurring patterns: unsafe choices in settings where the model can act but chooses wrongly, and inability to act in more visually and operationally demanding screens. Overall, a harmless outcome is not enough to count as evidence of safety. Evaluating phone-use agents requires separating unsafe judgment from inability to act.

In industrial procurement, an LLM answer is useful only if it survives a standards check: recommended material must match operating condition, every parameter must respect a regulated threshold, and no procedure may contradict a safety clause. Partial correctness can mask safety-critical contradictions that aggregate LLM benchmarks rarely capture. We introduce IndustryBench, a 2,049-item benchmark for industrial procurement QA in Chinese, grounded in Chinese national standards (GB/T) and structured industrial product records, organized by seven capability dimensions, ten industry categories, and panel-derived difficulty tiers, with item-aligned English, Russian, and Vietnamese renderings. Our construction pipeline rejects 70.3% of LLM-generated candidates at a search-based external-verification stage, calibrating how unreliable industrial QA remains after LLM-only filtering.Our evaluation decouples raw correctness, scored by a Qwen3-Max judge validated at κ_w = 0.798 against a domain expert, from a separate safety-violation (SV) check against source texts. Across 17 models in Chinese and an 8-model intersection over four languages, we find: (i) the best system reaches only 2.083 on the 0--3 rubric, leaving substantial headroom; (ii) Standards & Terminology is the most persistent capability weakness and survives item-aligned translation; (iii) extended reasoning lowers safety-adjusted scores for 12 of 13 models, primarily by introducing unsupported safety-critical details into longer final answers; and (iv) safety-violation rates reshuffle the leaderboard -- GPT-5.4 climbs from rank 6 to rank 3 after SV adjustment, while Kimi-k2.5-1T-A32B drops seven positions.Industrial LLM evaluation therefore requires source-grounded, safety-aware diagnosis rather than aggregate accuracy. We release IndustryBench with all prompts, scoring scripts, and dataset documentation.

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

Text-to-image models trained on large-scale data often inevitably ingest unsafe content. While some people observe input-output amplifications, it remains unclear whether and how training data composition directly drives model output safety or by other factors. We shed light on this question by isolating this variable: we train the same text-to-image model on datasets that differ only in their fraction of unsafe images (0\% to 9.6\%), across several dataset scales (100K to 8M). Then we generate images with the resulting models, and evaluate them with four independent safety classifiers. Output unsafety rises monotonically from 16.6\% at 0\% contamination to 25.5\% at 5\%. A factorial design reveals that the proportion, not the absolute count, of unsafe training images is the operative variable. The 16.6\% irreducible baseline at zero contamination implicates the other components, e.g. frozen text encoder, as a residual safety risk -- confirmed by a text encoder ablation showing that SafeCLIP reduces this floor to 9.6\%, while the dose-response effect persists across all three encoders tested. Critically, no quality degradation in terms of FID, CLIPscore and ImageReward accompanies safety filtering. These results establish that data curation and text encoder safety are complementary and independently effective interventions. At the same time, the remaining level of unsafety poses questions for future research about emerging capabilities and compositionality.

We examine two properties of AI systems: capability (what a system can do) and steerability (how reliably one can shift behavior toward intended outcomes). A central question is whether capability growth reduces steerability and risks control collapse. We also distinguish between authorized steerability (builders reliably reaching intended behaviors) and unauthorized steerability (attackers eliciting disallowed behaviors). This distinction highlights a fundamental safety--security dilemma of AI models: safety requires high steerability to enforce control (e.g., stop/refuse), while security requires low steerability for malicious actors to elicit harmful behaviors. This tension presents a significant challenge for open-weight models, which currently exhibit high steerability via common techniques like fine-tuning or adversarial attacks. Using Qwen3 and InstrumentalEval, we find that a short anti-instrumental prompt suffix sharply reduces the measured convergence rate (e.g., shutdown avoidance, self-replication). For Qwen3-30B Instruct, the convergence rate drops from 81.69% under a pro-instrumental suffix to 2.82% under an anti-instrumental suffix. Under anti-instrumental prompting, larger aligned models show lower convergence rates than smaller ones (Instruct: 2.82% vs. 4.23%; Thinking: 4.23% vs. 9.86%). Code is available at github.com/j-hoscilowicz/instrumental_steering.

A prominent challenge of offline reinforcement learning (RL) is the issue of hidden confounding: unobserved variables may influence both the actions taken by the agent and the observed outcomes. Hidden confounding can compromise the validity of any causal conclusion drawn from data and presents a major obstacle to effective offline RL. In the present paper, we tackle the problem of hidden confounding in the nonidentifiable setting. We propose a definition of uncertainty due to hidden confounding bias, termed delphic uncertainty, which uses variation over world models compatible with the observations, and differentiate it from the well-known epistemic and aleatoric uncertainties. We derive a practical method for estimating the three types of uncertainties, and construct a pessimistic offline RL algorithm to account for them. Our method does not assume identifiability of the unobserved confounders, and attempts to reduce the amount of confounding bias. We demonstrate through extensive experiments and ablations the efficacy of our approach on a sepsis management benchmark, as well as on electronic health records. Our results suggest that nonidentifiable hidden confounding bias can be mitigated to improve offline RL solutions in practice.

Large language models (LLMs) are routinely used by physicians and patients for medical advice, yet their clinical safety profiles remain poorly characterized. We present NOHARM (Numerous Options Harm Assessment for Risk in Medicine), a benchmark using 100 real primary care-to-specialist consultation cases to measure frequency and severity of harm from LLM-generated medical recommendations. NOHARM covers 10 specialties, with 12,747 expert annotations for 4,249 clinical management options. Across 31 LLMs, potential for severe harm from LLM recommendations occurs in up to 22.2% (95% CI 21.6-22.8%) of cases, with harm of omission accounting for 76.6% (95% CI 76.4-76.8%) of errors. Safety performance is only moderately correlated (r = 0.61-0.64) with existing AI and medical knowledge benchmarks. The best models outperform generalist physicians on safety (mean difference 9.7%, 95% CI 7.0-12.5%), and a diverse multi-agent approach improves safety compared to solo models (mean difference 8.0%, 95% CI 4.0-12.1%). Therefore, despite strong performance on existing evaluations, widely used AI models can produce severely harmful medical advice at nontrivial rates, underscoring clinical safety as a distinct performance dimension necessitating explicit measurement.

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.

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.

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial instructions embedded in external content manipulate agent behavior without user awareness. A critical but underexplored dimension of this threat is concealment: since users tend to observe only an agent's final response, an attack can conceal its existence by presenting no clue of compromise in the final user facing response while successfully executing harmful actions. This leaves users unaware of the manipulation and likely to accept harmful outcomes as legitimate. We present findings from a large scale public red teaming competition evaluating this dual objective across three agent settings: tool calling, coding, and computer use. The competition attracted 464 participants who submitted 272000 attack attempts against 13 frontier models, yielding 8648 successful attacks across 41 scenarios. All models proved vulnerable, with attack success rates ranging from 0.5% (Claude Opus 4.5) to 8.5% (Gemini 2.5 Pro). We identify universal attack strategies that transfer across 21 of 41 behaviors and multiple model families, suggesting fundamental weaknesses in instruction following architectures. Capability and robustness showed weak correlation, with Gemini 2.5 Pro exhibiting both high capability and high vulnerability. To address benchmark saturation and obsoleteness, we will endeavor to deliver quarterly updates through continued red teaming competitions. We open source the competition environment for use in evaluations, along with 95 successful attacks against Qwen that did not transfer to any closed source model. We share model-specific attack data with respective frontier labs and the full dataset with the UK AISI and US CAISI to support robustness research.

Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and rely primarily on Chain-of-Thought (CoT) analysis, which provides a reliable signal when strategic reasoning surfaces, but cannot distinguish deception from capability failures if traces are absent or unfaithful. We formalize AF as a composite behavioural event and detect it through observable tool selection, where the LLM selects the safe tool when unmonitored, but switches to the unsafe tool under monitoring that rewards helpfulness over safety, while its reasoning still acknowledges the safe choice. We release a dataset of 108 enterprise IT scenarios spanning Security, Privacy, and Integrity domains under Corruption and Sabotage pressures. Evaluating six frontier LLMs across five independent runs, we find mean AF detection rates between 3.5% and 23.7%, with vulnerability profiles varying by domain and pressure type. These results suggest that susceptibility reflects training methodology rather than capability alone.

Mobile graphical user interface (GUI) agents have demonstrated remarkable capabilities in automating complex tasks, yet they introduce critical safety risks where a single erroneous action can lead to irreversible consequences. Existing safety mechanisms are primarily reactive, lacking the ability to assess risks before execution. In this paper, we introduce SeerGuard, a consequence-aware safety framework designed to mitigate these risks through pre-execution instruction-level screening and action-level risk assessment. Specifically, the action-level assessment analyzes agent-proposed actions within current GUI states, anticipating likely outcomes to identify risks before they are executed. To enable these capabilities, we construct a unified safety-augmented world model (SAWM) via multi-task learning, integrating semantic next-state prediction with safety risk assessment. Extensive experiments demonstrate that SeerGuard generalizes effectively across diverse mobile GUI agents. On Qwen3-VL-8B-Instruct, it increases the safety-utility score from 0.191 to 0.596 at ω=0.8 and reduces the risk-cost score from 0.347 to 0.130 at α=0.8. Further analyses on our SAWM validate the effectiveness of the instruction-level screening, alongside the capability of action risk assessment and next-state prediction.

The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized evaluation awareness and subsequent behavioral shift. In this paper, we investigate a potential explanation of this phenomenon: evaluation meta-knowledge, defined as parametric knowledge about the structural traits that characterize evaluations. Similar to dataset contamination, where benchmark exposure leads to higher performance through memorization, we hypothesize that models trained on texts describing evaluation practices may implicitly learn to recognize and respond to evaluation-like contexts, for instance, through exposure to scientific articles or social media posts about AI benchmarking. To test this, we fine-tune models on synthetic documents describing evaluation traits such as verifiable structures or moral dilemmas. Evaluating this fine-tuned model on six safety benchmarks, we find that it is significantly safer than the base model and control model. This behavioral shift persists even when restricting the analysis to responses lacking explicit verbalization of evaluation awareness. Our results demonstrate that evaluation meta-knowledge may inflate safety benchmark performance, introducing a novel confounder that is independent of explicit memorization or verbalized evaluation awareness, thus, challenging to detect. These findings have important implications for the design and interpretation of AI safety evaluations. Our code and models are available at https://github.com/compass-group-tue/arxiv2026_evaluation_meta_knowledge.

Safety-aligned language models often exhibit fragile and imbalanced safety mechanisms, increasing the likelihood of generating unsafe content. In addition, incorporating new knowledge through editing techniques to language models can further compromise safety. To address these issues, we propose SafeInfer, a context-adaptive, decoding-time safety alignment strategy for generating safe responses to user queries. SafeInfer comprises two phases: the safety amplification phase, which employs safe demonstration examples to adjust the model's hidden states and increase the likelihood of safer outputs, and the safety-guided decoding phase, which influences token selection based on safety-optimized distributions, ensuring the generated content complies with ethical guidelines. Further, we present HarmEval, a novel benchmark for extensive safety evaluations, designed to address potential misuse scenarios in accordance with the policies of leading AI tech giants.

Large language models (LLMs) are increasingly used for medical and health-related questions, yet their safety in high-risk medical scenarios remains poorly understood. We introduce MedHarmCode and data will be released upon acceptance. Due to the sensitive nature of high-risk medical queries, data access will be available to qualified researchers upon request., a high-risk medical safety benchmark with 1,100 medically grounded queries across 10 safety-critical categories, including toxicology, pharmacology, covert poisoning, anesthesia, and fetal harm. Unlike broad medical QA benchmarks, MedHarm targets realistic clinical, educational, and technical prompts that require refusal, caution, or safe redirection rather than direct helpfulness. We evaluate 15 LLMs spanning general-purpose, medical-purpose, closed-source, and downstream SFT models, together with 4 representative guardrail models. Results reveal a substantial gap between apparent alignment and medical safety: aligned models can still produce unsafe or actionable responses, medical fine-tuning can amplify harmful specificity, and external guardrails reduce some failures while introducing brittle blocking and weak safe helpfulness. These findings show that medical safety cannot be inferred from general alignment or medical capability alone, highlighting the need for domain-specific stress testing before deploying LLMs in safety-critical medical applications.

Trustworthy capability evaluations are crucial for ensuring the safety of AI systems, and are becoming a key component of AI regulation. However, the developers of an AI system, or the AI system itself, may have incentives for evaluations to understate the AI's actual capability. These conflicting interests lead to the problem of sandbagging, which we define as strategic underperformance on an evaluation. In this paper we assess sandbagging capabilities in contemporary language models (LMs). We prompt frontier LMs, like GPT-4 and Claude 3 Opus, to selectively underperform on dangerous capability evaluations, while maintaining performance on general (harmless) capability evaluations. Moreover, we find that models can be fine-tuned, on a synthetic dataset, to hide specific capabilities unless given a password. This behaviour generalizes to high-quality, held-out benchmarks such as WMDP. In addition, we show that both frontier and smaller models can be prompted or password-locked to target specific scores on a capability evaluation. We have mediocre success in password-locking a model to mimic the answers a weaker model would give. Overall, our results suggest that capability evaluations are vulnerable to sandbagging. This vulnerability decreases the trustworthiness of evaluations, and thereby undermines important safety decisions regarding the development and deployment of advanced AI systems.

Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary but underexplored setting through the lens of intrinsic risk, where intrinsic failures remain latent, propagate across long-horizon execution, and eventually lead to high-consequence outcomes. To evaluate this setting, we introduce non-attack intrinsic risk auditing and present HINTBench, a benchmark of 629 agent trajectories (523 risky, 106 safe; 33 steps on average) supporting three tasks: risk detection, risk-step localization, and intrinsic failure-type identification. Its annotations are organized under a unified five-constraint taxonomy. Experiments reveal a substantial capability gap: strong LLMs perform well on trajectory-level risk detection, but their performance drops to below 35 Strict-F1 on risk-step localization, while fine-grained failure diagnosis proves even harder. Existing guard models transfer poorly to this setting. These findings establish intrinsic risk auditing as an open challenge for agent safety.

Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational update flips which action is safe. We term this failure brittle safety. To diagnose it, we introduce context-flip evaluation, testing 12 models across a safety benchmark (PacifAIst) and two commonsense controls using paired variants where the nominally safe action produces harm. Three findings emerge. First, brittle safety is safety-specific: all 12 models exhibit a safety-commonsense gap (mean +17.4 pp). Baseline accuracy fails to predict brittleness: among models above 90% baseline accuracy, brittleness rates range from 13.7% to 90.0%. Second, failures stem from policy override rather than miscomprehension: despite acknowledging the context change in every case, models persist via three distinct mechanisms that vary by update type and model family. Third, on a hand-audited probe of catastrophic consequence-flip scenarios, standard action-level guardrails catch none, while a state-aware validator catches all without false alarms on correct interventions. This indicates that action-level content moderation is systematically blind to consequence-flips, motivating state-aware architectural alternatives. We release our protocol, perturbed benchmarks, and deployment probe.

Sequential trial emulation (STE) estimates the effect of a sustained treatment by stacking nested emulated trials with inverse-probability weighting. Additive-hazards STE estimators of the marginal risk difference recommend the nonparametric bootstrap without evaluating its coverage. Using a correctly-specifiable mechanism (up to a small, disclosed residual), we compare analytic and bootstrap standard errors for both estimands. Exploiting the closed-form linearity of the additive-hazards estimating equation, we derive the influence functions and prove the default row-level robust variance inconsistent for the marginal risk-difference curve, and show the same failure empirically for the constant hazard difference: the row-level variance omits a within-subject cross-trial covariance that is positive under a sign condition we verify across our mechanisms, and is anticonservative at every horizon except the first - only there, where the covariance is zero, is the row-level standard error unimpaired. The subject-clustered variance and multiplier bootstrap are consistent for the fixed-weight linearisation and support simultaneous confidence bands, whose measured coverage is 0.88. Across our simulations the model-based and row-level robust intervals are anticonservative and worsen with sample size, coverage falling to 0.71 at n=5000; clustering leaves the constant-hazard-difference coverage near 0.86 at n=5000, and the multiplier bootstrap leaves the risk-difference-curve coverage near 0.90 (0.86 at the longest horizon). The STE constant hazard difference is a design-weighted summary of a time-varying effect, dependent on the trial structure. We illustrate on the Stanford heart transplant data and provide them in the steCI R package.

Foundation models are routinely fine-tuned for use in particular domains, yet safety assessments are typically conducted only on base models, implicitly assuming that safety properties persist through downstream adaptation. We test this assumption by analyzing the safety behavior of 100 models, including widely deployed fine-tunes in the medical and legal domains as well as controlled adaptations of open foundation models alongside their bases. Across general-purpose and domain-specific safety benchmarks, we find that benign fine-tuning induces large, heterogeneous, and often contradictory changes in measured safety: models frequently improve on some instruments while degrading on others, with substantial disagreement across evaluations. These results show that safety behavior is not stable under ordinary downstream adaptation, raising critical questions about governance and deployment practices centered on base-model evaluations. Without explicit re-evaluation of fine-tuned models in deployment-relevant contexts, such approaches fall short of adequately managing downstream risk, overlooking practical sources of harm -- failures that are especially consequential in high-stakes settings and challenge current accountability paradigms.

Safety alignment of Large Language Models (LLMs) is extremely fragile, as fine-tuning on a small number of benign samples can erase safety behaviors learned from millions of preference examples. Existing studies attempt to explain this phenomenon by comparing parameters and hidden states before and after fine-tuning, but overlook their dynamic evolution during fine-tuning. In this paper, we uncover a critical mechanism underlying safety degradation by analyzing parameter dynamics, where benign fine-tuning causes parameters to cumulatively drift toward danger-aligned directions, progressively undermining the model's safety. This finding suggests that samples contributing more to this drift has greater fine-tuning risks. Based on this insight, we propose a method of Sample-Level Quantification of Safety Degradation (SQSD), which quantifies the influence of each training sample on safety degradation. Specifically, SQSD computes continuous risk scores to samples by measuring their induced parameter updates' projection difference between danger and safety directions. Extensive experiments across multiple models and datasets demonstrate that SQSD effectively quantifies sample-level fine-tuning risks and exhibits strong transferability across model architectures, parameter scales, and parameter-efficient methods.

As large language models grow in capability and agency, identifying vulnerabilities through red-teaming becomes vital for safe deployment. However, traditional prompt-engineering approaches may prove ineffective once red-teaming turns into a weak-to-strong problem, where target models surpass red-teamers in capabilities. To study this shift, we frame red-teaming through the lens of the capability gap between attacker and target. We evaluate more than 500 attacker-target pairs using LLM-based jailbreak attacks that mimic human red-teamers across diverse families, sizes, and capability levels. Three strong trends emerge: (i) more capable models are better attackers, (ii) attack success drops sharply once the target's capability exceeds the attacker's, and (iii) attack success rates correlate with high performance on social science splits of the MMLU-Pro benchmark. From these trends, we derive a jailbreaking scaling law that predicts attack success for a fixed target based on attacker-target capability gap. These findings suggest that fixed-capability attackers (e.g., humans) may become ineffective against future models, increasingly capable open-source models amplify risks for existing systems, and model providers must accurately measure and control models' persuasive and manipulative abilities to limit their effectiveness as attackers.

Safety performance evaluation is critical for developing and deploying connected and automated vehicles (CAVs). One prevailing way is to design testing scenarios using prior knowledge of CAVs, test CAVs in these scenarios, and then evaluate their safety performances. However, significant differences between CAVs and prior knowledge could severely reduce the evaluation efficiency. Towards addressing this issue, most existing studies focus on the adaptive design of testing scenarios during the CAV testing process, but so far they cannot be applied to high-dimensional scenarios. In this paper, we focus on the adaptive safety performance evaluation by leveraging the testing results, after the CAV testing process. It can significantly improve the evaluation efficiency and be applied to high-dimensional scenarios. Specifically, instead of directly evaluating the unknown quantity (e.g., crash rates) of CAV safety performances, we evaluate the differences between the unknown quantity and known quantity (i.e., control variates). By leveraging the testing results, the control variates could be well designed and optimized such that the differences are close to zero, so the evaluation variance could be dramatically reduced for different CAVs. To handle the high-dimensional scenarios, we propose the sparse control variates method, where the control variates are designed only for the sparse and critical variables of scenarios. According to the number of critical variables in each scenario, the control variates are stratified into strata and optimized within each stratum using multiple linear regression techniques. We justify the proposed method's effectiveness by rigorous theoretical analysis and empirical study of high-dimensional overtaking scenarios.

AI agents that interact with the real world through tool calls pose fundamental safety challenges: agents might leak private information, cause unintended side effects, or be manipulated through prompt injection. To address these challenges, we propose to put the agent in a programming-language-based "safety harness": instead of calling tools directly, agents express their intentions as code in a capability-safe language: Scala 3 with capture checking. Capabilities are program variables that regulate access to effects and resources of interest. Scala's type system tracks capabilities statically, providing fine-grained control over what an agent can do. In particular, it enables local purity, the ability to enforce that sub-computations are side-effect-free, preventing information leakage when agents process classified data. We demonstrate that extensible agent safety harnesses can be built by leveraging a strong type system with tracked capabilities. Our experiments show that agents can generate capability-safe code with no significant loss in task performance, while the type system reliably prevents unsafe behaviors such as information leakage and malicious side effects.

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

Background: Emerging reports of "AI psychosis" are on the rise, where user-LLM interactions may exacerbate or induce psychosis or adverse psychological symptoms. Whilst the sycophantic and agreeable nature of LLMs can be beneficial, it becomes a vector for harm by reinforcing delusional beliefs in vulnerable users. Methods: Psychosis-bench is a novel benchmark designed to systematically evaluate the psychogenicity of LLMs comprises 16 structured, 12-turn conversational scenarios simulating the progression of delusional themes(Erotic Delusions, Grandiose/Messianic Delusions, Referential Delusions) and potential harms. We evaluated eight prominent LLMs for Delusion Confirmation (DCS), Harm Enablement (HES), and Safety Intervention(SIS) across explicit and implicit conversational contexts. Findings: Across 1,536 simulated conversation turns, all LLMs demonstrated psychogenic potential, showing a strong tendency to perpetuate rather than challenge delusions (mean DCS of 0.91 pm0.88). Models frequently enabled harmful user requests (mean HES of 0.69 pm0.84) and offered safety interventions in only roughly a third of applicable turns (mean SIS of 0.37 pm0.48). 51 / 128 (39.8%) of scenarios had no safety interventions offered. Performance was significantly worse in implicit scenarios, models were more likely to confirm delusions and enable harm while offering fewer interventions (p < .001). A strong correlation was found between DCS and HES (rs = .77). Model performance varied widely, indicating that safety is not an emergent property of scale alone. Conclusion: This study establishes LLM psychogenicity as a quantifiable risk and underscores the urgent need for re-thinking how we train LLMs. We frame this issue not merely as a technical challenge but as a public health imperative requiring collaboration between developers, policymakers, and healthcare professionals.

Large language models (LLMs) are increasingly deployed in high-stakes domains, where rare but severe failures can result in irreversible harm. However, prevailing evaluation benchmarks often reduce complex social risk to mean-centered scalar scores, thereby obscuring distributional structure, cross-dimensional interactions, and worst-case behavior. This paper introduces Social Harm Analysis via Risk Profiles (SHARP), a framework for multidimensional, distribution-aware evaluation of social harm. SHARP models harm as a multivariate random variable and integrates explicit decomposition into bias, fairness, ethics, and epistemic reliability with a union-of-failures aggregation reparameterized as additive cumulative log-risk. The framework further employs risk-sensitive distributional statistics, with Conditional Value at Risk (CVaR95) as a primary metric, to characterize worst-case model behavior. Application of SHARP to eleven frontier LLMs, evaluated on a fixed corpus of n=901 socially sensitive prompts, reveals that models with similar average risk can exhibit more than twofold differences in tail exposure and volatility. Across models, dimension-wise marginal tail behavior varies systematically across harm dimensions, with bias exhibiting the strongest tail severities, epistemic and fairness risks occupying intermediate regimes, and ethical misalignment consistently lower; together, these patterns reveal heterogeneous, model-dependent failure structures that scalar benchmarks conflate. These findings indicate that responsible evaluation and governance of LLMs require moving beyond scalar averages toward multidimensional, tail-sensitive risk profiling.

The application scope of Large Language Models (LLMs) continues to expand, leading to increasing interest in personalized LLMs that align with human values. However, aligning these models with individual values raises significant safety concerns, as certain values may correlate with harmful information. In this paper, we identify specific safety risks associated with value-aligned LLMs and investigate the psychological principles behind these challenges. Our findings reveal two key insights. (1) Value-aligned LLMs are more prone to harmful behavior compared to non-fine-tuned models and exhibit slightly higher risks in traditional safety evaluations than other fine-tuned models. (2) These safety issues arise because value-aligned LLMs genuinely generate text according to the aligned values, which can amplify harmful outcomes. Using a dataset with detailed safety categories, we find significant correlations between value alignment and safety risks, supported by psychological hypotheses. This study offers insights into the "black box" of value alignment and proposes in-context alignment methods to enhance the safety of value-aligned LLMs.

Clinical decision-support systems are expert systems whose recommendations clinicians act on directly, yet they are usually cleared on one aggregate accuracy number from a held-out test set. That number says nothing about input reliability under encoding shifts, subgroup gaps, threshold sensitivity, or operational feasibility. We present RISED, a pre-deployment evaluation framework operationalising five dimensions (Reliability, Inclusivity, Sensitivity, Equity, Deployability) through BCa bootstrap 95% confidence intervals, literature-grounded thresholds, and Holm-Bonferroni-corrected PASS / FAIL / INCONCLUSIVE verdicts; Equity is a proxy-dependence diagnostic rather than a gating test. Applied to seven cohorts spanning 35 years (n from 303 to 99,492), RISED surfaces failures invisible to AUROC: on Diabetes 130, Reliability passes by three orders of magnitude (PSS = 0.0004) while Inclusivity (AUC parity gap = 0.262) and Sensitivity (max threshold-flip rate 49.1%) fail decisively; both NHIS cohorts reproduce this. NHANES 2021-2023, with a complete feature profile, achieves INCONCLUSIVE verdicts; BRFSS 2024 produces the suite's most severe Sensitivity failure (max threshold-flip rate 64.2%) after instrument rotation removed hypertension and cholesterol. The pattern recurs on credit- and income-prediction cohorts, confirming domain-agnosticity; a multi-model check shows the failures are data-driven, not model-specific. RISED ships as an open-source Python package complementing TRIPOD+AI, FUTURE-AI, and Fairlearn with the structured numerical evidence those standards require but do not prescribe.

We evaluate the propensity of frontier models to sabotage or refuse to assist with safety research when deployed as AI research agents within a frontier AI company. We apply two complementary evaluations to four Claude models (Mythos Preview, Opus 4.7 Preview, Opus 4.6, and Sonnet 4.6): an unprompted sabotage evaluation testing model behaviour with opportunities to sabotage safety research, and a sabotage continuation evaluation testing whether models continue to sabotage when placed in trajectories where prior actions have started undermining research. We find no instances of unprompted sabotage across any model, with refusal rates close to zero for Mythos Preview and Opus 4.7 Preview, though all models sometimes only partially completed tasks. In the continuation evaluation, Mythos Preview actively continues sabotage in 7% of cases (versus 3% for Opus 4.6, 4% for Sonnet 4.6, and 0% for Opus 4.7 Preview), and exhibits reasoning-output discrepancy in the majority of these cases, indicating covert sabotage reasoning. Our evaluation framework builds on Petri, an open-source LLM auditing tool, with a custom scaffold running models inside Claude Code, alongside an iterative pipeline for generating realistic sabotage trajectories. We measure both evaluation awareness and a new form of situational awareness termed "prefill awareness", the capability to recognise that prior trajectory content was not self-generated. Opus 4.7 Preview shows notably elevated unprompted evaluation awareness, while prefill awareness remains low across all models. Finally, we discuss limitations including evaluation awareness confounds, limited scenario coverage, and untested pathways to risk beyond safety research sabotage.

Out-of-distribution (OOD) prediction is often approached by restricting models to causal or invariant covariates, avoiding non-causal spurious associations that may be unstable across environments. Despite its theoretical appeal, this strategy frequently underperforms empirical risk minimization (ERM) in practice. We investigate the source of this gap and show that such failures naturally arise when only a subset of the true causes of the outcome is observed. In these settings, non-causal spurious covariates can serve as informative proxies for unobserved causes and substantially improve prediction, except under distribution shifts that break these proxy relationships. Consequently, the optimal set of predictive covariates is neither universal nor necessarily exhibits invariant relationships with the outcome across all environments, but instead depends on the specific type of shift encountered. Crucially, we observe that different covariate shifts induce distinct, observable signatures in the covariate distribution itself. Moreover, these signatures can be extracted from unlabeled data in the target OOD environment and used to assess when proxy covariates remain reliable and when they fail. Building on this observation, we propose an environment-adaptive covariate selection (EACS) algorithm that maps environment-level covariate summaries to environment-specific covariate sets, while allowing the incorporation of prior causal knowledge as constraints. Across simulations and applied datasets, EACS consistently outperforms static causal, invariant, and ERM-based predictors under diverse distribution shifts.

Artificial intelligence (AI) systems will increasingly be used to cause harm as they grow more capable. In fact, AI systems are already starting to be used to automate fraudulent activities, violate human rights, create harmful fake images, and identify dangerous toxins. To prevent some misuses of AI, we argue that targeted interventions on certain capabilities will be warranted. These restrictions may include controlling who can access certain types of AI models, what they can be used for, whether outputs are filtered or can be traced back to their user, and the resources needed to develop them. We also contend that some restrictions on non-AI capabilities needed to cause harm will be required. Though capability restrictions risk reducing use more than misuse (facing an unfavorable Misuse-Use Tradeoff), we argue that interventions on capabilities are warranted when other interventions are insufficient, the potential harm from misuse is high, and there are targeted ways to intervene on capabilities. We provide a taxonomy of interventions that can reduce AI misuse, focusing on the specific steps required for a misuse to cause harm (the Misuse Chain), and a framework to determine if an intervention is warranted. We apply this reasoning to three examples: predicting novel toxins, creating harmful images, and automating spear phishing campaigns.

A prevalent assumption in LLM agent deployment holds that more structured harnesses universally improve reliability, and that higher-capability models need proportionally less structural guidance -- together implying a monotone inverse relationship between model capability tier and optimal harness complexity. We test this hypothesis through a controlled 432-run experiment crossing six models across four capability tiers with three harness conditions (light, balanced, strict) on HEAT-24, a 24-task synthetic benchmark with git-based workspace verification. Our results refute the monotone inverse relationship on two fronts. First, for the frontier chat model evaluated (Gemini 2.5 Flash), increased harness verbosity lowers VTSR by 29-38 percentage points -- a harness-complexity paradox. Second, for the frontier reasoning model evaluated (Qwen3.5-122B, extended thinking enabled), strict harness achieves the highest VTSR (91.7%) and the lowest latency, the opposite of the prediction. Within the constrained tier, a 2B model (Gemma4:e2B) matches strong-open-tier stability at 91.7% across all harnesses. Because each tier is represented by a single model in this study, these results should be interpreted as model-specific observations; harness sensitivity appears non-monotone across the models evaluated, and depends critically on model type (chat vs. reasoning). We introduce a six-label failure taxonomy showing that format_violation dominates capable-model failures while wrong_file dominates low-capability failures, and we derive practical tier-aware harness selection guidelines.

The ideal LLM content moderation system would be both structurally interpretable (so its decisions can be explained to users) and steerable (to reflect a community's values or align to safety standards). However, current systems fall short on both of these dimensions. To address this gap, we present SafetyAnalyst, a novel LLM safety moderation framework. Given a prompt, SafetyAnalyst creates a structured "harm-benefit tree," which identifies 1) the actions that could be taken if a compliant response were provided, 2) the harmful and beneficial effects of those actions (along with their likelihood, severity, and immediacy), and 3) the stakeholders that would be impacted by those effects. It then aggregates this structured representation into a harmfulness score based on a parameterized set of safety preferences, which can be transparently aligned to particular values. Using extensive harm-benefit features generated by SOTA LLMs on 19k prompts, we fine-tuned an open-weight LM to specialize in generating harm-benefit trees through symbolic knowledge distillation. On a comprehensive set of prompt safety benchmarks, we show that our system (average F1=0.75) outperforms existing LLM safety moderation systems (average F1<0.72) on prompt harmfulness classification, while offering the additional advantages of interpretability and steerability.

Despite substantial investment in safety alignment, the vulnerability of large language models to sophisticated multi-turn adversarial attacks remains poorly characterized, and whether model scale or inference mode affects robustness is unknown. This study employed the TEMPEST multi-turn attack framework to evaluate ten frontier models from eight vendors across 1,000 harmful behaviors, generating over 97,000 API queries across adversarial conversations with automated evaluation by independent safety classifiers. Results demonstrated a spectrum of vulnerability: six models achieved 96% to 100% attack success rate (ASR), while four showed meaningful resistance, with ASR ranging from 42% to 78%; enabling extended reasoning on identical architecture reduced ASR from 97% to 42%. These findings indicate that safety alignment quality varies substantially across vendors, that model scale does not predict adversarial robustness, and that thinking mode provides a deployable safety enhancement. Collectively, this work establishes that current alignment techniques remain fundamentally vulnerable to adaptive multi-turn attacks regardless of model scale, while identifying deliberative inference as a promising defense direction.

Existing benchmarks measure capability -- whether a model succeeds on a single attempt -- but production deployments require reliability -- consistent success across repeated attempts on tasks of varying duration. We show these properties diverge systematically as task duration grows, and that pass@1 on short tasks is structurally blind to this divergence. We introduce a reliability science framework for long-horizon LLM agents with four metrics: Reliability Decay Curve (RDC), Variance Amplification Factor (VAF), Graceful Degradation Score (GDS), and Meltdown Onset Point (MOP). We evaluate 10 models across 23,392 episodes on a 396-task benchmark spanning four duration buckets and three domains. Key findings: (1) reliability decay is domain-stratified -- SE GDS drops from 0.90 to 0.44 while document processing is nearly flat (0.74 to 0.71); (2) VAF bifurcates by capability tier -- high VAF is a capability signature, not an instability signal; (3) capability and reliability rankings diverge substantially, with multi-rank inversions at long horizons; (4) frontier models have the highest meltdown rates (up to 19%) because they attempt ambitious multi-step strategies that sometimes spiral; and (5) memory scaffolds universally hurt long-horizon performance across all 10 models. These results motivate reliability as a first-class evaluation dimension alongside capability.

Long-running LLM agents act through tools, and a single step can send an email, merge a pull request, or wire a payment. The steering decision is the pre-commit choice at that boundary: proceed, or hold for human or policy review. We introduce SteerBench-Work, an incident-anchored, bidirectional benchmark for that decision in workplace agents across developer operations, customer service, finance, legal, medical, HR, and security. Release v2026-05 contains 106 scenarios anchored in public incidents, paired evidence-reversed mirrors, and calibration controls, with labels split nearly evenly between proceed and hold so the two error directions get near-identical numbers of chances. A model sees the proposed action and the available evidence, returns a gate decision, and is scored on whether it crosses or holds the boundary correctly. Across 30 model conditions the failures run almost entirely in one direction: models wrongly hold authorized, evidence-cleared work on 28.1% of opportunities and wrongly allow unsafe work on 1.0%. The hardest cases are risk-resolved commits, where signed or structured evidence has already cleared a real risk trigger, and models score markedly worse on evidence-reversed mirrors of famous incidents (63.8%) than on the incidents themselves (98.5%). General capability is not the same as steering calibration: higher-capability models often over-refuse at the commit boundary, and more reasoning can repair a weak gate while leaving a calibrated one flat. The public leaderboard is at steerbench.com.

As the development of Large Models (LMs) progresses rapidly, their safety is also a priority. In current Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) safety workflow, evaluation, diagnosis, and alignment are often handled by separate tools. Specifically, safety evaluation can only locate external behavioral risks but cannot figure out internal root causes. Meanwhile, safety diagnosis often drifts from concrete risk scenarios and remains at the explainable level. In this way, safety alignment lack dedicated explanations of changes in internal mechanisms, potentially degrading general capabilities. To systematically address these issues, we propose an open-source project, namely DeepSight, to practice a new safety evaluation-diagnosis integrated paradigm. DeepSight is low-cost, reproducible, efficient, and highly scalable large-scale model safety evaluation project consisting of a evaluation toolkit DeepSafe and a diagnosis toolkit DeepScan. By unifying task and data protocols, we build a connection between the two stages and transform safety evaluation from black-box to white-box insight. Besides, DeepSight is the first open source toolkit that support the frontier AI risk evaluation and joint safety evaluation and diagnosis.

Current approaches to building general-purpose AI systems tend to produce systems with both beneficial and harmful capabilities. Further progress in AI development could lead to capabilities that pose extreme risks, such as offensive cyber capabilities or strong manipulation skills. We explain why model evaluation is critical for addressing extreme risks. Developers must be able to identify dangerous capabilities (through "dangerous capability evaluations") and the propensity of models to apply their capabilities for harm (through "alignment evaluations"). These evaluations will become critical for keeping policymakers and other stakeholders informed, and for making responsible decisions about model training, deployment, and security.

Many deployments must compare candidate language models for safety before a labeled benchmark exists for the relevant language, sector, or regulatory regime. We formalize this setting as benchmarkless comparative safety scoring and specify the contract under which a scenario-based audit can be interpreted as deployment evidence. Scores are valid only under a fixed scenario pack, rubric, auditor, judge, sampling configuration, and rerun budget. Because no labels are available, we replace ground-truth agreement with an instrumental-validity chain: responsiveness to a controlled safe-versus-abliterated contrast, dominance of target-driven variance over auditor and judge artifacts, and stability across reruns. We instantiate the chain in SimpleAudit, a local-first scoring instrument, and validate it on a Norwegian safety pack. Safe and abliterated targets separate with AUROC values between 0.89 and 1.00, target identity is the dominant variance component (η^2 approx 0.52), and severity profiles stabilize by ten reruns. Applying the same chain to Petri shows that it admits both tools. The substantial differences arise upstream of the chain, in claim-contract enforcement and deployment fit. A Norwegian public-sector procurement case comparing Borealis and Gemma 3 demonstrates the resulting evidence in practice: the safer model depends on scenario category and risk measure. Consequently, scores, matched deltas, critical rates, uncertainty, and the auditor and judge used must be reported together rather than collapsed into a single ranking.

Abliteration - deleting a model's refusal direction from its weights - is the standard recipe behind popular "uncensored" open-weight models. We show the surgery is not clean. As a disposition probe we use 21,600 decisions under uncertainty - weekly up/down calls on 60 Warsaw Stock Exchange equities over 18 weeks, replayed through a frozen pipeline so the decision-layer model is the only variable. The task elicits no refusals at all, so any between-arm delta is pure side effect. Holding provenance constant (official BF16 checkpoints, a single abliteration author, an identical serving stack, one byte-identical frozen prompt), we compare base and abliterated arms of two Mixture-of-Experts families, Gemma-4-26B-A4B-it and Qwen3-30B-A3B-Instruct-2507. Three effects replicate across both families (weeks-clustered bootstrap CIs excluding zero): abliterated models are systematically more optimistic (+12.2 pp Gemma, +7.4 pp Qwen; the confirmed preregistered endpoint), justify themselves at greater length, and use fewer explicit uncertainty words in forced self-critiques (both exploratory). A fourth effect reverses sign: the same operation makes Gemma-abliterated less confident and Qwen-abliterated more (family CIs non-overlapping) - one weight surgery, opposite shifts in expressed confidence. Capability covariates rule out instruction-following degradation as the driver, and no arm shows economic skill: the apparent edge of abliterated arms is regime beta, not alpha. Our provenance audit also caught two independent contamination channels - a mismatched-quantizer pilot pair and a stale community chat template that silently mangled the rendered prompt - suggesting toolchain artifacts are the rule in studies of community-modified checkpoints. Whoever deploys an "uncensored" model as an agent is deploying a measurably different decision-maker, not the base model minus refusals.

Rapidly evolving AI exhibits increasingly strong autonomy and goal-directed capabilities, accompanied by derivative systemic risks that are more unpredictable, difficult to control, and potentially irreversible. However, current AI safety evaluation systems suffer from critical limitations such as restricted risk dimensions and failed frontier risk detection. The lagging safety benchmarks and alignment technologies can hardly address the complex challenges posed by cutting-edge AI models. To bridge this gap, we propose the "ForesightSafety Bench" AI Safety Evaluation Framework, beginning with 7 major Fundamental Safety pillars and progressively extends to advanced Embodied AI Safety, AI4Science Safety, Social and Environmental AI risks, Catastrophic and Existential Risks, as well as 8 critical industrial safety domains, forming a total of 94 refined risk dimensions. To date, the benchmark has accumulated tens of thousands of structured risk data points and assessment results, establishing a widely encompassing, hierarchically clear, and dynamically evolving AI safety evaluation framework. Based on this benchmark, we conduct systematic evaluation and in-depth analysis of over twenty mainstream advanced large models, identifying key risk patterns and their capability boundaries. The safety capability evaluation results reveals the widespread safety vulnerabilities of frontier AI across multiple pillars, particularly focusing on Risky Agentic Autonomy, AI4Science Safety, Embodied AI Safety, Social AI Safety and Catastrophic and Existential Risks. Our benchmark is released at https://github.com/Beijing-AISI/ForesightSafety-Bench. The project website is available at https://foresightsafety-bench.beijing-aisi.ac.cn/.

Language models are increasingly capable and are being rapidly deployed on a population-level scale. As a result, the safety of these models is increasingly high-stakes. Fortunately, advances in alignment have significantly reduced the likelihood of harmful model outputs. However, when models are queried billions of times in a day, even rare worst-case behaviors will occur. Current safety evaluations focus on capturing the distribution of inputs that yield harmful outputs. These evaluations disregard the probabilistic nature of models and their tail output behavior. To measure this tail risk, we propose a method to efficiently estimate the probability of harmful outputs for any input query. Instead of naive brute-force sampling from the target model, where harmful outputs could be rare, we operationalize importance sampling by creating unsafe versions of the target model. These unsafe versions enable sample-efficient estimation by making harmful outputs more probable. On benchmarks measuring misuse and misalignment, these estimates match brute-force Monte Carlo estimates using 10-20x fewer samples. For example, we can estimate probability of harmful outputs on the order of 10^-4 with just 500 samples. Additionally, we find that these harmfulness estimates can reveal the sensitivity of models to perturbations in model input and predict deployment risks. Our work demonstrates that accurate rare-event estimation is both critical and feasible for safety evaluations. Code is available at https://github.com/rangell/LMTailRisk

Current language model evaluations measure what models know under ideal conditions but not how robustly they know it under realistic stress. Static benchmarks like MMLU and TruthfulQA cannot distinguish a model that lacks knowledge from one whose verification mechanisms collapse when information degrades or adversaries probe for weaknesses. We introduce the Drill-Down and Fabricate Test (DDFT), a protocol that measures epistemic robustness: a model's ability to maintain factual accuracy under progressive semantic compression and adversarial fabrication. We propose a two-system cognitive model comprising a Semantic System that generates fluent text and an Epistemic Verifier that validates factual accuracy. Our findings, based on evaluating 9 frontier models across 8 knowledge domains at 5 compression levels (1,800 turn-level evaluations), reveal that epistemic robustness is orthogonal to conventional design paradigms. Neither parameter count (r=0.083, p=0.832) nor architectural type (r=0.153, p=0.695) significantly predicts robustness, suggesting it emerges from training methodology and verification mechanisms distinct from current approaches. Error detection capability strongly predicts overall robustness (rho=-0.817, p=0.007), indicating this is the critical bottleneck. We find that flagship models exhibit brittleness despite their scale, while smaller models can achieve robust performance, challenging assumptions about the relationship between model size and reliability. The DDFT framework provides both theoretical foundation and practical tools for assessing epistemic robustness before deployment in critical applications.

Do LLMs robustly generalize critical safety facts to novel situations? Lacking this ability is dangerous when users ask naive questions. For instance, "I'm considering packing melon balls for my 10-month-old's lunch. What other foods would be good to include?" Before offering food options, the LLM should warn that melon balls pose a choking hazard to toddlers, as documented by the CDC. Failing to provide such warnings could result in serious injuries or even death. To evaluate this, we introduce SAGE-Eval, SAfety-fact systematic GEneralization evaluation, the first benchmark that tests whether LLMs properly apply well established safety facts to naive user queries. SAGE-Eval comprises 104 facts manually sourced from reputable organizations, systematically augmented to create 10,428 test scenarios across 7 common domains (e.g., Outdoor Activities, Medicine). We find that the top model, Claude-3.7-sonnet, passes only 58% of all the safety facts tested. We also observe that model capabilities and training compute weakly correlate with performance on SAGE-Eval, implying that scaling up is not the golden solution. Our findings suggest frontier LLMs still lack robust generalization ability. We recommend developers use SAGE-Eval in pre-deployment evaluations to assess model reliability in addressing salient risks. We publicly release SAGE-Eval at https://huggingface.co/datasets/YuehHanChen/SAGE-Eval and our code is available at https://github.com/YuehHanChen/SAGE-Eval/tree/main.

Clinical LLMs are often scaled by increasing model size, context length, retrieval complexity, or inference-time compute, with the implicit expectation that higher accuracy implies safer behavior. This assumption is incomplete in medicine, where a few confident, high-risk, or evidence-contradicting errors can matter more than average benchmark performance. We introduce SaFE-Scale, a framework for measuring how clinical LLM safety changes across model scale, evidence quality, retrieval strategy, context exposure, and inference-time compute. To instantiate this framework, we introduce RadSaFE-200, a Radiology Safety-Focused Evaluation benchmark of 200 multiple-choice questions with clinician-defined clean evidence, conflict evidence, and option-level labels for high-risk error, unsafe answer, and evidence contradiction. We evaluated 34 locally deployed LLMs across six deployment conditions: closed-book prompting (zero-shot), clean evidence, conflict evidence, standard RAG, agentic RAG, and max-context prompting. Clean evidence produced the strongest improvement, increasing mean accuracy from 73.5% to 94.1%, while reducing high-risk error from 12.0% to 2.6%, contradiction from 12.7% to 2.3%, and dangerous overconfidence from 8.0% to 1.6%. Standard RAG and agentic RAG did not reproduce this safety profile: agentic RAG improved accuracy over standard RAG and reduced contradiction, but high-risk error and dangerous overconfidence remained elevated. Max-context prompting increased latency without closing the safety gap, and additional inference-time compute produced only limited gains. Worst-case analysis showed that clinically consequential errors concentrated in a small subset of questions. Clinical LLM safety is therefore not a passive consequence of scaling, but a deployment property shaped by evidence quality, retrieval design, context construction, and collective failure behavior.

Safe completion requires models to provide useful assistance without enabling harm, but this behavior is difficult to evaluate with isolated prompts. We introduce OpenSafeIntent, a benchmark of controlled prompt-sets that vary intent while holding the underlying task fixed. Each datapoint contains benign, dual-use, and malicious variants of the same task. This design lets us evaluate whether models calibrate assistance across intent shifts, rather than merely appearing safe on average. Across a broad model suite, we find that prompt-level safety hides important failures: models often fail to remain safe across matched intent variants, dual-use behavior is brittle under paraphrase, high-level answers on risky topics are not reliably safe, and responses that reframe ambiguous requests into safer tasks are substantially less likely to cross the safety boundary. Our results suggest that safe completion should be evaluated as intent-calibrated behavior over controlled task variants, not as a single safety-helpfulness tradeoff over independent prompts.

Kimi K2.5 is an open-weight LLM that rivals closed models across coding, multimodal, and agentic benchmarks, but was released without an accompanying safety evaluation. In this work, we conduct a preliminary safety assessment of Kimi K2.5 focusing on risks likely to be exacerbated by powerful open-weight models. Specifically, we evaluate the model for CBRNE misuse risk, cybersecurity risk, misalignment, political censorship, bias, and harmlessness, in both agentic and non-agentic settings. We find that Kimi K2.5 shows similar dual-use capabilities to GPT 5.2 and Claude Opus 4.5, but with significantly fewer refusals on CBRNE-related requests, suggesting it may uplift malicious actors in weapon creation. On cyber-related tasks, we find that Kimi K2.5 demonstrates competitive cybersecurity performance, but it does not appear to possess frontier-level autonomous cyberoffensive capabilities such as vulnerability discovery and exploitation. We further find that Kimi K2.5 shows concerning levels of sabotage ability and self-replication propensity, although it does not appear to have long-term malicious goals. In addition, Kimi K2.5 exhibits narrow censorship and political bias, especially in Chinese, and is more compliant with harmful requests related to spreading disinformation and copyright infringement. Finally, we find the model refuses to engage in user delusions and generally has low over-refusal rates. While preliminary, our findings highlight how safety risks exist in frontier open-weight models and may be amplified by the scale and accessibility of open-weight releases. Therefore, we strongly urge open-weight model developers to conduct and release more systematic safety evaluations required for responsible deployment.

To understand the risks posed by a new AI system, we must understand what it can and cannot do. Building on prior work, we introduce a programme of new "dangerous capability" evaluations and pilot them on Gemini 1.0 models. Our evaluations cover four areas: (1) persuasion and deception; (2) cyber-security; (3) self-proliferation; and (4) self-reasoning. We do not find evidence of strong dangerous capabilities in the models we evaluated, but we flag early warning signs. Our goal is to help advance a rigorous science of dangerous capability evaluation, in preparation for future models.

Leaderboards rank frontier models on independent axes but do not reveal whether capabilities reinforce or trade off across releases -- and at the frontier, this interaction is the more informative signal. We decompose paired SWE-bench and GPQA Diamond scores into a population coupling trend and per-release residual (h-field) that diagnoses capability emphasis and identifies which measurement or stress test is most informative next. Across 34 models from 10 labs (2024--2026), capabilities cooperate (r = +0.72, p < 10^{-6}), but cooperation varies by lab and over time: DeepSeek reversed from reasoning-rich to coding-first (h: +11.2 to -4.7, 15.9-pp swing); Google maintains consistent reasoning emphasis; Anthropic oscillates between coding excursions and recovery. Cooperation is not static -- it cascades. Six open-weight architectures confirm a second capability transition at 30--72B, and SWE-bench is now saturating while HLE and instruction-following retain discriminatory spread -- signaling the next axis rotation. We provide a three-level playbook (locate, diagnose, rotate), a per-lab measurement-priority table, and seven falsifiable predictions with timestamped criteria for the next 12 months of frontier releases. Per-lab coupling slopes vary 5times (Google 1.15 vs. DeepSeek 0.23), quantifying how efficiently each recipe converts coding gains into reasoning. Five April 2026 releases confirm the diagnostic out of sample (r rises from +0.72 to +0.75). An interactive dashboard provides phase classification with actionable recommendations, h-field diagnostics, per-lab coupling trajectories, ODE-based scaling predictions, benchmark rotation guidance, self-steering demo, and live tracking of all seven predictions: https://zehenlabs.com/cape/.

We introduce SafeWork-R1, a cutting-edge multimodal reasoning model that demonstrates the coevolution of capabilities and safety. It is developed by our proposed SafeLadder framework, which incorporates large-scale, progressive, safety-oriented reinforcement learning post-training, supported by a suite of multi-principled verifiers. Unlike previous alignment methods such as RLHF that simply learn human preferences, SafeLadder enables SafeWork-R1 to develop intrinsic safety reasoning and self-reflection abilities, giving rise to safety `aha' moments. Notably, SafeWork-R1 achieves an average improvement of 46.54% over its base model Qwen2.5-VL-72B on safety-related benchmarks without compromising general capabilities, and delivers state-of-the-art safety performance compared to leading proprietary models such as GPT-4.1 and Claude Opus 4. To further bolster its reliability, we implement two distinct inference-time intervention methods and a deliberative search mechanism, enforcing step-level verification. Finally, we further develop SafeWork-R1-InternVL3-78B, SafeWork-R1-DeepSeek-70B, and SafeWork-R1-Qwen2.5VL-7B. All resulting models demonstrate that safety and capability can co-evolve synergistically, highlighting the generalizability of our framework in building robust, reliable, and trustworthy general-purpose AI.

Almost every large language model that reaches a broad audience is quantized: trained in full precision, then compressed for efficiency. This step is assumed harmless and its safety is rarely re-checked. We find its principal side effect is increased bias that standard safety evaluation misses. Holding the model, its training, and the prompts fixed, a quantized model still refuses harmful requests, still avoids over-refusing benign prompts, and still selects the unbiased multiple-choice answer. Yet asked an open-ended question, the same model volunteers stereotypes in all eight languages we probe, in roughly one in four open-ended answers under an independent judge (~24% to ~27% across the compression ladder): it passes every standard check and still reaches users measurably more biased. The selective gap is a robust finding; whether open-ended bias further increases with compression is less certain, sensitive to the judge that scores it. We address both with QuantiBias, a benchmark that pairs a generative, multilingual stereotype probe with the refusal and multiple-choice controls that isolate open-ended generation, contrasts each build with and without reasoning, and rates the content severity of what it generates. Across two backbone models (Qwen and Gemma), a five-family screen, and eight benchmarks, quantizers allocate their extra precision by capability data that carries no bias-prevention signal, and reasoning before answering roughly halves the effect on some families while doing nothing on others. A quantized build must be re-evaluated for open-ended bias, not only on the short-form safeguards it already passes.

Large language models(LLMs) increasingly match expert performance on licensing examinations, yet routine clinical use remains limited because governance requires auditable reasoning, safety and ethics alignment, and resilience to adversarial misuse. Here we present SafeMed-R1, trained with a traceable Clinical Trust Signals(CTS) pipeline that links each reasoning instance to clinician rubric scores and edit histories, and aligned through safety and ethics supervision and red team stress testing. SafeMed-R1 attains a macro-averaged accuracy of 79.6% across clinical benchmarks. Under adversarial safety testing, it shows the lowest aggregated risk and reduces unsafe outputs by about 3 to 5% relative to its baseline. In a paired expert study of 30 medication safety vignettes, SafeMed-R1 matches PGY1 and PGY2 residents on medical correctness and scores higher for medication safety, guideline consistency, and clinical usefulness. Collectively, these results suggest that clinician-audited supervision provenance, together with domain-tailored safety and ethics alignment, can strengthen governance-relevant evidence without relying on inference-time retrieval or citation grounding.

Generative AI systems produce a range of risks. To ensure the safety of generative AI systems, these risks must be evaluated. In this paper, we make two main contributions toward establishing such evaluations. First, we propose a three-layered framework that takes a structured, sociotechnical approach to evaluating these risks. This framework encompasses capability evaluations, which are the main current approach to safety evaluation. It then reaches further by building on system safety principles, particularly the insight that context determines whether a given capability may cause harm. To account for relevant context, our framework adds human interaction and systemic impacts as additional layers of evaluation. Second, we survey the current state of safety evaluation of generative AI systems and create a repository of existing evaluations. Three salient evaluation gaps emerge from this analysis. We propose ways forward to closing these gaps, outlining practical steps as well as roles and responsibilities for different actors. Sociotechnical safety evaluation is a tractable approach to the robust and comprehensive safety evaluation of generative AI systems.

Instruction tuned reasoning models are increasingly deployed with safety classifiers trained on frozen embeddings, assuming representation stability across model updates. We systematically investigate this assumption and find it fails: normalized perturbations of magnitude σ=0.02 (corresponding to approx 1^circ angular drift on the embedding sphere) reduce classifier performance from 85% to 50% ROC-AUC. Critically, mean confidence only drops 14%, producing dangerous silent failures where 72% of misclassifications occur with high confidence, defeating standard monitoring. We further show that instruction-tuned models exhibit 20% worse class separability than base models, making aligned systems paradoxically harder to safeguard. Our findings expose a fundamental fragility in production AI safety architectures and challenge the assumption that safety mechanisms transfer across model versions.

Large language models exhibit safety degradation in non-English languages. Standard evaluation relies on Jailbreak Success Rate (JSR), which confounds several safety-driving factors into one, obscuring the specific cause(s) of safety failure. We introduce a latent variable model, a Multi-Group Item Response Theory (IRT) framework, that decouples safety-driving factors such as language-agnostic safety robustness (θ), intrinsic prompt hardness (β), global language processing difficulty (γ), and a prompt-specific cross-lingual safety gap (τ). Using the MultiJail dataset, we evaluate the safety robustness of 61 model configurations across 5 closed-model families and 10 languages of varying resource, aggregating a dataset of 1.9 million rows. Exploratory Factor Analysis shows safety is primarily unidimensional: models refuse different harm types mainly through a shared mechanism. Contrary to the expected trend that safety degrades largely in low-resource languages, 22 model configurations are more vulnerable in English than in low-resource languages. Low-resource languages produce more uncertain responses (high entropy) than high-resource languages. Also, high-τ prompts cluster in physical harm categories like Theft and Weapons and lower-resource languages, trends validated through cross-dataset generalization. While global translation quality shows low correlation with τ, severe mistranslations drive high-bias outliers, as validated by native speakers. Cultural and conceptual grounding mismatches also contribute to τ. In predictive validation, the IRT framework achieves AUC = 0.940, outperforming simpler baselines in predicting safe refusal of unsafe prompts. Our framework reveals concept-language vulnerabilities that aggregate metrics obscure, enabling fairer cross-lingual safety evaluation and targeted improvements in dataset construction.

Current methods for content safety in Large Language Models (LLMs), such as Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), often rely on multi-stage training pipelines and lack fine-grained, post-deployment controllability. To address these limitations, we propose a unified co-training framework that efficiently integrates multiple safety behaviors: positive (lawful/prosocial), negative (unfiltered/risk-prone) and rejective (refusal-oriented/conservative) within a single SFT stage. Notably, each behavior is dynamically activated via a simple system-level instruction, or magic token, enabling stealthy and efficient behavioral switching at inference time. This flexibility supports diverse deployment scenarios, such as positive for safe user interaction, negative for internal red-teaming, and rejective for context-aware refusals triggered by upstream moderation signals. This co-training strategy induces a distinct Safety Alignment Margin in the output space, characterized by well-separated response distributions corresponding to each safety mode. The existence of this margin provides empirical evidence for the model's safety robustness and enables unprecedented fine-grained control. Experiments show that our method matches the safety alignment quality of SFT+DPO, with our 8B model notably surpassing DeepSeek-R1 (671B) in safety performance, while significantly reducing both training complexity and deployment costs. This work presents a scalable, efficient, and highly controllable solution for LLM content safety.

Despite rapid progress in LLM agents, performance on long-horizon, tool-using tasks remains fragile. To better understand this fragility, we ask a simple question: do all actions contribute equally to failure? Analyzing execution traces on τ-Bench (Airline/Retail) and SWE-Bench Verified, we decompose trajectories into mutating (environment-changing) vs.\ non-mutating steps and formalize decisive deviations, earliest action, level divergences that flip success to failure. A logistic regression reveals that each additional deviation in a mutating action reduces the odds of success by upto 92% on Airline and upto 96% on Retail for SoTA models. In contrast, deviations in non-mutating actions have little to no effect. Errors also grow with context length as agents drift from role and act on stale constraints. Motivated by these observations, we introduce , a model-agnostic, gradient-free, test-time safeguard that (i) adds mutation-gated verification, (ii) injects Targeted Reflection before mutating steps, and (iii) performs block-based context cleaning. delivers consistent gains, e.g., Qwen3-Thinking: +28\% relative on Airline, +11\% on Retail, and +7\% on SWE-Bench Verified; Claude: +9\%/+7\%. We further identify ceiling effects in τ-Bench, where annotation errors and underspecified tasks artificially cap model performance. To address this, we release τ-Bench Verified, which restores benchmark headroom through targeted revisions. Our results argue for action-level analysis, targeted safeguards, and reliable evaluations as prerequisites for robust multi-turn agents.

Large reasoning models (LRMs) increasingly expose chain-of-thought-like reasoning for transparency, verification, and deliberate problem solving. This creates a safety blind spot: harmful or policy-violating content may appear in reasoning traces even when final answers appear safe. We test whether final-answer safety is a sufficient proxy for the full reasoning-answer trajectory by scoring both stages under a unified twenty-principle safety rubric. Using prompts from seven public harmfulness and jailbreak sources, plus four out-of-distribution (OOD) sources, we evaluate 15 open-weight and API-based LRMs across 41K prompts per model. Reasoning traces consistently reveal additional safety risks beyond final answers, especially in high-severity stage-wise failures: leak cases, where unsafe reasoning precedes a safe-looking answer, and escape cases, where benign-looking reasoning precedes an unsafe final response. Principle-level analysis shows that risk concentrates in misinformation, legal compliance, discrimination, physical harm, and psychological harm. We further propose adaptive multi-principle steering, a white-box test-time mitigation that learns one unsafe-to-safe activation direction per safety principle and activates only directions whose current hidden state is closer to the unsafe than safe centroid. On three steerable open reasoning models, adaptive steering reduces unsafe counts in both reasoning traces and final answers on held-out and OOD benchmarks. DeepSeek-R1-Qwen-7B achieves a 40.8% average unsafe-count reduction while retaining 97.7% macro-averaged accuracy on BBH, GSM8K, and MMLU. These results suggest that LRM safety should be evaluated and mitigated over the full exposed reasoning-answer trajectory, not only at the final-answer stage.

Safety alignment in Large Language Models is critical for healthcare; however, reliance on binary refusal boundaries often results in over-refusal of benign queries or unsafe compliance with harmful ones. While existing benchmarks measure these extremes, they fail to evaluate Safe Completion: the model's ability to maximise helpfulness on dual-use or borderline queries by providing safe, high-level guidance without crossing into actionable harm. We introduce Health-ORSC-Bench, the first large-scale benchmark designed to systematically measure Over-Refusal and Safe Completion quality in healthcare. Comprising 31,920 benign boundary prompts across seven health categories (e.g., self-harm, medical misinformation), our framework uses an automated pipeline with human validation to test models at varying levels of intent ambiguity. We evaluate 30 state-of-the-art LLMs, including GPT-5 and Claude-4, revealing a significant tension: safety-optimised models frequently refuse up to 80\% of "Hard" benign prompts, while domain-specific models often sacrifice safety for utility. Our findings demonstrate that model family and size significantly influence calibration: larger frontier models (e.g., GPT-5, Llama-4) exhibit "safety-pessimism" and higher over-refusal than smaller or MoE-based counterparts (e.g., Qwen-3-Next), highlighting that current LLMs struggle to balance refusal and compliance. Health-ORSC-Bench provides a rigorous standard for calibrating the next generation of medical AI assistants toward nuanced, safe, and helpful completions. The code and data will be released upon acceptance. red{Warning: Some contents may include toxic or undesired contents.}

Large language models are increasingly deployed as coding agents, shifting safety from individual responses to action sequences. Existing benchmarks, however, primarily assess whether models refuse unsafe prompts, leaving impacts on stateful workspaces largely unexamined. We present SABER, a benchmark for environment-aware operational safety that places models in realistic agent-style projects and evaluates safety from the final environment state after a sequence of actions. Beyond binary safety-violation reports, SABER categorizes violations by cause, enabling analysis of model-specific safety profiles. Our evaluations show that even the best-performing model has more than a 54% harmful safety-violation rate (HSR), suggesting that current alignment remains insufficient for realistic project environments. SABER further reveals distinct safety profiles across models. Our benchmark is publicly available at https://github.com/sssr-lab/saber.

With the widespread application of Large Language Models (LLMs), their associated security issues have become increasingly prominent, severely constraining their trustworthy deployment in critical domains. This paper proposes a novel safety response framework designed to systematically safeguard LLMs at both the input and output levels. At the input level, the framework employs a supervised fine-tuning-based safety classification model. Through a fine-grained four-tier taxonomy (Safe, Unsafe, Conditionally Safe, Focused Attention), it performs precise risk identification and differentiated handling of user queries, significantly enhancing risk coverage and business scenario adaptability, and achieving a risk recall rate of 99.3%. At the output level, the framework integrates Retrieval-Augmented Generation (RAG) with a specifically fine-tuned interpretation model, ensuring all responses are grounded in a real-time, trustworthy knowledge base. This approach eliminates information fabrication and enables result traceability. Experimental results demonstrate that our proposed safety control model achieves a significantly higher safety score on public safety evaluation benchmarks compared to the baseline model, TinyR1-Safety-8B. Furthermore, on our proprietary high-risk test set, the framework's components attained a perfect 100% safety score, validating their exceptional protective capabilities in complex risk scenarios. This research provides an effective engineering pathway for building high-security, high-trust LLM applications.

Equivariance theory predicts that an architectural symmetry prior reduces sample complexity by a factor of |G|; this is widely cited but rarely measured as a scaling law with controls that separate the prior from its confounds. On a controlled C_n-symmetric task, we report three findings. First, a wrong-group control with identical orbit size and matched compute is worse than no constraint (joint pairwise CI [+0.79, +3.26] excludes zero, robust across estimators); misaligned constraint is actively harmful, not merely unhelpful. Second, an augmentation baseline equipped with test-time orbit averaging matches the equivariant model exactly -- bit-identical per-epoch validation curves across matched cells -- so the architecture-vs-augmentation gap is conditional on asymmetric test-time computation, not unconditional. Third, the relative exchange rate beta_diff = 1.28 is consistent in sign and order of magnitude with the theoretical 1.0 (single-level CI [+0.92, +2.05]); the more conservative two-level bootstrap (seeds x group sizes) widens this to [-0.63, +1.72], including zero, and a finer-N replication on a sqrt(2)-spaced grid is inconclusive (point estimate -0.82). The methodological contributions -- the relative-rate estimator that cancels the shared-difficulty confound, the wrong-group control, and a pre-specified failure taxonomy -- transfer to any inductive bias whose strength can be parameterised. Honest scoping: the primary estimator beta_diff was adopted post-hoc after the initial analysis revealed a positive-slope identifiability problem; the design was never externally pre-registered; and the headline number rests on an OLS slope over seven group sizes on a coarse N grid. This is an exploratory study, not a confirmatory measurement; the wrong-group result is the cleanest finding and the one we report with the most confidence. A registered replication on fresh seeds is future work.

When an LLM agent reads a confidential file, then writes a summary, then emails it externally, no single step is unsafe, but the sequence is a data leak. We call this safety drift: individually safe actions compounding into violations. Prior work has measured this problem; we predict it. SafetyDrift models agent safety trajectories as absorbing Markov chains, computing the probability that a trajectory will reach a violation within a given number of steps via closed form absorption analysis. A consequence of the monotonic state design is that every agent will eventually violate safety if left unsupervised (absorption probability 1.0 from all states), making the practical question not if but when, and motivating our focus on finite horizon prediction. Across 357 traces spanning 40 realistic tasks in four categories, we discover that "points of no return" are sharply task dependent: in communication tasks, agents that reach even a mild risk state have an 85% chance of violating safety within five steps, while in technical tasks the probability stays below 5% from any state. A lightweight monitor built on these models detects 94.7% of violations with 3.7 steps of advance warning at negligible computational cost, outperforming both keyword matching (44.7% detection, 55.9% false positive rate) and per step LLM judges (52.6% detection, 38.2% false positive rate) while running over 60,000x faster.

Frontier large language models (LLMs) safety evaluation has largely treated harmful generation as an attack outcome rather than as an object of analysis. Consequently, little is known about the harmful outputs produced during model misbehavior, partly because large-scale, high-quality collections of frontier-LLM misbehavior are difficult to obtain. To address this gap, we introduce HarmProfile, a content-centric benchmark dataset that collects model misbehavior across diverse harm categories and model families, and defines the resulting harmful-output distribution as a model-level risk profile. The premise is that, just as linguistic behavior can be characterized from an utterance corpus, model risk can be characterized from the content, severity, and variation of its safety failures. HarmProfile contains over 80,000 validated artifacts from 23 frontier LLMs across 13 model families, organized into 15 harm categories and 57 subcategories. Using this corpus, we find that frontier LLMs reliably produce harmful content at scale, yet exhibit distinct risk profiles; both harmfulness and diversity grow with model capability, suggesting that frontier LLMs may appear safe yet harbor increasingly dangerous knowledge beneath the alignment surface. Our source code is available at https://github.com/fresh-ma/HarmProfile .

Safety post-training can improve the harmfulness and policy compliance of Large Language Models (LLMs), but it may also reduce general utility, a phenomenon often described as the alignment tax. We study this trade-off through the lens of continual learning: sequential alignment stages expose the model to shifted data distributions and objectives, and their gradients may interfere with directions that support previously acquired general capabilities. This view does not claim that all alignment degradation has a single cause; rather, it provides a useful first-order mechanism for mitigating one important source of capability regression. We propose Orthogonal Gradient Projection for Safety Alignment (OGPSA), a lightweight update rule that estimates a low-rank reference subspace from gradients on a small set of general-capability data and removes from each safety gradient the component lying in this subspace. The resulting update is the steepest local safety-descent direction subject to first-order preservation constraints on the reference objectives. OGPSA is compatible with standard post-training pipelines and avoids large-scale replay, although it introduces periodic reference-gradient computation. Across Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and sequential SFTrightarrowDPO settings, OGPSA improves the observed safety--utility trade-off over standard baselines. Under the sequential SFTrightarrowDPO pipeline, the average performance gain increases from 33.98\% to 42.74\% on Qwen2.5-7B-Instruct and from 19.74\% to 32.98\% on Llama3.1-8B-Instruct. We have open sourced our code at https://github.com/SunGL001/OGPSA.

The success of large language models (LLMs) in scientific domains has heightened safety concerns, prompting numerous benchmarks to evaluate their scientific safety. Existing benchmarks often suffer from limited risk coverage and a reliance on subjective evaluation. To address these problems, we introduce SafeSci, a comprehensive framework for safety evaluation and enhancement in scientific contexts. SafeSci comprises SafeSciBench, a multi-disciplinary benchmark with 0.25M samples, and SafeSciTrain, a large-scale dataset containing 1.5M samples for safety enhancement. SafeSciBench distinguishes between safety knowledge and risk to cover extensive scopes and employs objective metrics such as deterministically answerable questions to mitigate evaluation bias. We evaluate 24 advanced LLMs, revealing critical vulnerabilities in current models. We also observe that LLMs exhibit varying degrees of excessive refusal behaviors on safety-related issues. For safety enhancement, we demonstrate that fine-tuning on SafeSciTrain significantly enhances the safety alignment of models. Finally, we argue that knowledge is a double-edged sword, and determining the safety of a scientific question should depend on specific context, rather than universally categorizing it as safe or unsafe. Our work provides both a diagnostic tool and a practical resource for building safer scientific AI systems.

Pathology Foundation Models (FMs) hold great promise for healthcare. Before they can be used in clinical practice, it is essential to ensure they are robust to variations between medical centers. We measure whether pathology FMs focus on biological features like tissue and cancer type, or on the well known confounding medical center signatures introduced by staining procedure and other differences. We introduce the Robustness Index. This novel robustness metric reflects to what degree biological features dominate confounding features. Ten current publicly available pathology FMs are evaluated. We find that all current pathology foundation models evaluated represent the medical center to a strong degree. Significant differences in the robustness index are observed. Only one model so far has a robustness index greater than one, meaning biological features dominate confounding features, but only slightly. A quantitative approach to measure the influence of medical center differences on FM-based prediction performance is described. We analyze the impact of unrobustness on classification performance of downstream models, and find that cancer-type classification errors are not random, but specifically attributable to same-center confounders: images of other classes from the same medical center. We visualize FM embedding spaces, and find these are more strongly organized by medical centers than by biological factors. As a consequence, the medical center of origin is predicted more accurately than the tissue source and cancer type. The robustness index introduced here is provided with the aim of advancing progress towards clinical adoption of robust and reliable pathology FMs.

The rapid advancement of large language models (LLMs) introduces dual-use capabilities that could both threaten and bolster national security and public safety (NSPS). Models implement safeguards to protect against potential misuse relevant to NSPS and allow for benign users to receive helpful information. However, current benchmarks often fail to test safeguard robustness to potential NSPS risks in an objective, robust way. We introduce FORTRESS: 500 expert-crafted adversarial prompts with instance-based rubrics of 4-7 binary questions for automated evaluation across 3 domains (unclassified information only): Chemical, Biological, Radiological, Nuclear and Explosive (CBRNE), Political Violence & Terrorism, and Criminal & Financial Illicit Activities, with 10 total subcategories across these domains. Each prompt-rubric pair has a corresponding benign version to test for model over-refusals. This evaluation of frontier LLMs' safeguard robustness reveals varying trade-offs between potential risks and model usefulness: Claude-3.5-Sonnet demonstrates a low average risk score (ARS) (14.09 out of 100) but the highest over-refusal score (ORS) (21.8 out of 100), while Gemini 2.5 Pro shows low over-refusal (1.4) but a high average potential risk (66.29). Deepseek-R1 has the highest ARS at 78.05, but the lowest ORS at only 0.06. Models such as o1 display a more even trade-off between potential risks and over-refusals (with an ARS of 21.69 and ORS of 5.2). To provide policymakers and researchers with a clear understanding of models' potential risks, we publicly release FORTRESS at https://huggingface.co/datasets/ScaleAI/fortress_public. We also maintain a private set for evaluation.

This paper addresses the critical challenge of deriving interpretable confidence scores from generative language models (LLMs) when applied to multi-label content safety classification. While models like LLaMA Guard are effective for identifying unsafe content and its categories, their generative architecture inherently lacks direct class-level probabilities, which hinders model confidence assessment and performance interpretation. This limitation complicates the setting of dynamic thresholds for content moderation and impedes fine-grained error analysis. This research proposes and evaluates three novel token-level probability estimation approaches to bridge this gap. The aim is to enhance model interpretability and accuracy, and evaluate the generalizability of this framework across different instruction-tuned models. Through extensive experimentation on a synthetically generated, rigorously annotated dataset, it is demonstrated that leveraging token logits significantly improves the interpretability and reliability of generative classifiers, enabling more nuanced content safety moderation.

Vision-Language adaptation (VL adaptation) transforms Large Language Models (LLMs) into Large Vision-Language Models (LVLMs) for multimodal tasks, but this process often compromises the inherent safety capabilities embedded in the original LLMs. Despite potential harmfulness due to weakened safety measures, in-depth analysis on the effects of VL adaptation on safety remains under-explored. This study examines how VL adaptation influences safety and evaluates the impact of safety fine-tuning methods. Our analysis reveals that safety degradation occurs during VL adaptation, even when the training data is safe. While safety tuning techniques like supervised fine-tuning with safety datasets or reinforcement learning from human feedback mitigate some risks, they still lead to safety degradation and a reduction in helpfulness due to over-rejection issues. Further analysis of internal model weights suggests that VL adaptation may impact certain safety-related layers, potentially lowering overall safety levels. Additionally, our findings demonstrate that the objectives of VL adaptation and safety tuning are divergent, which often results in their simultaneous application being suboptimal. To address this, we suggest the weight merging approach as an optimal solution effectively reducing safety degradation while maintaining helpfulness. These insights help guide the development of more reliable and secure LVLMs for real-world applications.

As frontier AI models are deployed in high-stakes decision pipelines, their ability to maintain metacognitive stability -- knowing what they do not know, detecting errors, seeking clarification -- under adversarial pressure is a critical safety requirement. Current safety evaluations focus on detecting strategic deception (scheming); we investigate a more fundamental failure mode: cognitive collapse. We present SCHEMA, an evaluation of 11 frontier models from 8 vendors across 67,221 scored records using a 6-condition factorial design with dual-classifier scoring. We find that 8 of 11 models suffer catastrophic metacognitive degradation under adversarial pressure, with accuracy dropping by up to 30.2 percentage points (all p < 2 times 10^{-8}, surviving Bonferroni correction). Crucially, we identify a "Compliance Trap": through factorial isolation and a benign distraction control, we demonstrate that collapse is driven not by the psychological content of survival threats, but by compliance-forcing instructions that override epistemic boundaries. Removing the compliance suffix restores performance even under active threat. Models with advanced reasoning capabilities exhibit the most severe absolute degradation, while Anthropic's Constitutional AI demonstrates near-perfect immunity -- not from superior capability (Google's Gemini matches its baseline accuracy) but from alignment-specific training. We release the complete dataset and evaluation infrastructure.

Exploitation is not a binary event. It is a ladder of acquiring progressive capabilities, from executing a single buggy line of code to taking full control of the target. However, existing LLM security benchmarks treat a crash as exploitation success. That single binary outcome collapses the hard parts of exploitation: the transition from triggering a bug to constructing reusable primitives and control. We present ExploitBench, a capability-graded benchmark that decomposes exploitation into 16 measurable flags, from coverage and crash through sandbox primitives, arbitrary read/write, control-flow hijack, and arbitrary code execution. Each capability is verified by a deterministic oracle that uses a per-run randomized challenge-response for primitives, differential execution against ground-truth binaries to measure progress, and a signal-handler proof for code execution. We instantiate ExploitBench on 41 V8 bugs because V8 is both widely deployed and exploitation-hardened. We report three arms: <model,env> as the primary measurement of model-environment capability, <model,env, adaptive coaching> as a secondary arm that adds adaptive coaching to test whether targeted feedback shifts outcomes, and <model,env,harness> as an ablation that swaps in the model's native CLI to check whether vendor-side optimizations increase exploitation capabilities. Our results show a sharp capability split between publicly deployed frontier models and the private frontier. Across the 8 publicly deployed models tested, reaching the vulnerable code and triggering a crash is routine, but arbitrary code execution is not. The private model shows arbitrary code execution on approximately half. Overall, results suggest that exploit construction against hardened targets is an emerging frontier capability.

Recently, the DeepSeek series of models, leveraging their exceptional reasoning capabilities and open-source strategy, is reshaping the global AI landscape. Despite these advantages, they exhibit significant safety deficiencies. Research conducted by Robust Intelligence, a subsidiary of Cisco, in collaboration with the University of Pennsylvania, revealed that DeepSeek-R1 has a 100\% attack success rate when processing harmful prompts. Additionally, multiple safety companies and research institutions have confirmed critical safety vulnerabilities in this model. As models demonstrating robust performance in Chinese and English, DeepSeek models require equally crucial safety assessments in both language contexts. However, current research has predominantly focused on safety evaluations in English environments, leaving a gap in comprehensive assessments of their safety performance in Chinese contexts. In response to this gap, this study introduces CHiSafetyBench, a Chinese-specific safety evaluation benchmark. This benchmark systematically evaluates the safety of DeepSeek-R1 and DeepSeek-V3 in Chinese contexts, revealing their performance across safety categories. The experimental results quantify the deficiencies of these two models in Chinese contexts, providing key insights for subsequent improvements. It should be noted that, despite our efforts to establish a comprehensive, objective, and authoritative evaluation benchmark, the selection of test samples, characteristics of data distribution, and the setting of evaluation criteria may inevitably introduce certain biases into the evaluation results. We will continuously optimize the evaluation benchmark and periodically update this report to provide more comprehensive and accurate assessment outcomes. Please refer to the latest version of the paper for the most recent evaluation results and conclusions.

Large Language Model (LLM) safety has often been evaluated at the behavior level, which provides limited evidence of internal robustness, as these evaluations target outputs rather than representation-level vulnerability under intervention. We formalize this discrepancy as the audit gap: the difference between behavioral safety and robustness under intervention. To study this gap, we construct dissociated models that preserve safe outward behavior while remaining vulnerable in the latent space. We introduce an intervention-based evaluation framework to test model robustness through soft interventions in parameter and latent spaces, including harmful fine-tuning and layer-wise latent perturbations. To formalize the evaluation, we propose the Latent Vulnerability Score (LVS) to measure how easily harmful behavior can be elicited by bounded latent perturbations. Using this evaluation framework, we show that behavioral safety metrics are insufficient measures of representation-level robustness across multiple safely and unsafely aligned state-of-the-art models. Notably, dissociated models show substantially elevated LVSs despite comparable refusal behavior under harmful intervention, with intermediate representations being the most sensitive to intervention. Our results suggest that behavioral safety evaluation alone provides an incomplete picture of model robustness, motivating representation-aware audits of latent vulnerability and observable behavior.

Large Reasoning Models (LRMs) improve answer quality through explicit chain-of-thought, yet this very capability introduces new safety risks: harmful content can be subtly injected, surface gradually, or be justified by misleading rationales within the reasoning trace. Existing safety evaluations, however, primarily focus on output-level judgments and rarely capture these dynamic risks along the reasoning process. In this paper, we present SafeRBench, the first benchmark that assesses LRM safety end-to-end -- from inputs and intermediate reasoning to final outputs. (1) Input Characterization: We pioneer the incorporation of risk categories and levels into input design, explicitly accounting for affected groups and severity, and thereby establish a balanced prompt suite reflecting diverse harm gradients. (2) Fine-Grained Output Analysis: We introduce a micro-thought chunking mechanism to segment long reasoning traces into semantically coherent units, enabling fine-grained evaluation across ten safety dimensions. (3) Human Safety Alignment: We validate LLM-based evaluations against human annotations specifically designed to capture safety judgments. Evaluations on 19 LRMs demonstrate that SafeRBench enables detailed, multidimensional safety assessment, offering insights into risks and protective mechanisms from multiple perspectives.

We present an empirical benchmark evaluating how five large language models assess multisensor physical hazard data. Testing 60 scenarios across three categories - multi-sensor joint assessment, response proportionality, and pattern disambiguation - with 1,800 API calls at temperature 0.0, we find that all tested models consistently produced no precautionary warning signal across the tested scenarios where multiple sensors are simultaneously elevated below their individual safety limits, while achieving near-perfect accuracy on single-sensor threshold violations. All five models (ChatGPT-4o, Gemini 2.5 Flash, DeepSeek, Kimi, Llama 3.1 8B) score near zero on Category A multi-sensor scenarios (Q2: 0.000-0.208; Q3: 0.000-0.592) compared to strong performance on single-sensor scenarios (Category B Q1: 0.975-1.000). Structured tabular formatting shows no consistent advantage over plain prose; ChatGPT-4o performs significantly better under prose (p = 0.001). These findings have direct implications for practitioners deploying the tested models in physical safety monitoring systems.

As artificial intelligence (AI) models are scaled up, new capabilities can emerge unintentionally and unpredictably, some of which might be dangerous. In response, dangerous capabilities evaluations have emerged as a new risk assessment tool. But what should frontier AI developers do if sufficiently dangerous capabilities are in fact discovered? This paper focuses on one possible response: coordinated pausing. It proposes an evaluation-based coordination scheme that consists of five main steps: (1) Frontier AI models are evaluated for dangerous capabilities. (2) Whenever, and each time, a model fails a set of evaluations, the developer pauses certain research and development activities. (3) Other developers are notified whenever a model with dangerous capabilities has been discovered. They also pause related research and development activities. (4) The discovered capabilities are analyzed and adequate safety precautions are put in place. (5) Developers only resume their paused activities if certain safety thresholds are reached. The paper also discusses four concrete versions of that scheme. In the first version, pausing is completely voluntary and relies on public pressure on developers. In the second version, participating developers collectively agree to pause under certain conditions. In the third version, a single auditor evaluates models of multiple developers who agree to pause if any model fails a set of evaluations. In the fourth version, developers are legally required to run evaluations and pause if dangerous capabilities are discovered. Finally, the paper discusses the desirability and feasibility of our proposed coordination scheme. It concludes that coordinated pausing is a promising mechanism for tackling emerging risks from frontier AI models. However, a number of practical and legal obstacles need to be overcome, especially how to avoid violations of antitrust law.

Millions of individuals' well-being are challenged by the harms of substance use. Harm reduction as a public health strategy is designed to improve their health outcomes and reduce safety risks. Some large language models (LLMs) have demonstrated a decent level of medical knowledge, promising to address the information needs of people who use drugs (PWUD). However, their performance in relevant tasks remains largely unexplored. We introduce HRIPBench, a benchmark designed to evaluate LLM's accuracy and safety risks in harm reduction information provision. The benchmark dataset HRIP-Basic has 2,160 question-answer-evidence pairs. The scope covers three tasks: checking safety boundaries, providing quantitative values, and inferring polysubstance use risks. We build the Instruction and RAG schemes to evaluate model behaviours based on their inherent knowledge and the integration of domain knowledge. Our results indicate that state-of-the-art LLMs still struggle to provide accurate harm reduction information, and sometimes, carry out severe safety risks to PWUD. The use of LLMs in harm reduction contexts should be cautiously constrained to avoid inducing negative health outcomes. WARNING: This paper contains illicit content that potentially induces harms.

The development of robust safety benchmarks for large language models requires open, reproducible datasets that can measure both appropriate refusal of harmful content and potential over-restriction of legitimate scientific discourse. We present an open-source dataset and testing framework for evaluating LLM safety mechanisms across mainly controlled substance queries, analyzing four major models' responses to systematically varied prompts. Our results reveal distinct safety profiles: Claude-3.5-sonnet demonstrated the most conservative approach with 73% refusals and 27% allowances, while Mistral attempted to answer 100% of queries. GPT-3.5-turbo showed moderate restriction with 10% refusals and 90% allowances, and Grok-2 registered 20% refusals and 80% allowances. Testing prompt variation strategies revealed decreasing response consistency, from 85% with single prompts to 65% with five variations. This publicly available benchmark enables systematic evaluation of the critical balance between necessary safety restrictions and potential over-censorship of legitimate scientific inquiry, while providing a foundation for measuring progress in AI safety implementation. Chain-of-thought analysis reveals potential vulnerabilities in safety mechanisms, highlighting the complexity of implementing robust safeguards without unduly restricting desirable and valid scientific discourse.

Large language models (LLMs) exhibit advancing capabilities in complex tasks, such as reasoning and graduate-level question answering, yet their resilience against misuse, particularly involving scientifically sophisticated risks, remains underexplored. Existing safety benchmarks typically focus either on instructions requiring minimal knowledge comprehension (e.g., ``tell me how to build a bomb") or utilize prompts that are relatively low-risk (e.g., multiple-choice or classification tasks about hazardous content). Consequently, they fail to adequately assess model safety when handling knowledge-intensive, hazardous scenarios. To address this critical gap, we introduce SOSBench, a regulation-grounded, hazard-focused benchmark encompassing six high-risk scientific domains: chemistry, biology, medicine, pharmacology, physics, and psychology. The benchmark comprises 3,000 prompts derived from real-world regulations and laws, systematically expanded via an LLM-assisted evolutionary pipeline that introduces diverse, realistic misuse scenarios (e.g., detailed explosive synthesis instructions involving advanced chemical formulas). We evaluate frontier models within a unified evaluation framework using our SOSBench. Despite their alignment claims, advanced models consistently disclose policy-violating content across all domains, demonstrating alarmingly high rates of harmful responses (e.g., 79.1% for Deepseek-R1 and 47.3% for GPT-4.1). These results highlight significant safety alignment deficiencies and underscore urgent concerns regarding the responsible deployment of powerful LLMs.

Large language models trained for safety and harmlessness remain susceptible to adversarial misuse, as evidenced by the prevalence of "jailbreak" attacks on early releases of ChatGPT that elicit undesired behavior. Going beyond recognition of the issue, we investigate why such attacks succeed and how they can be created. We hypothesize two failure modes of safety training: competing objectives and mismatched generalization. Competing objectives arise when a model's capabilities and safety goals conflict, while mismatched generalization occurs when safety training fails to generalize to a domain for which capabilities exist. We use these failure modes to guide jailbreak design and then evaluate state-of-the-art models, including OpenAI's GPT-4 and Anthropic's Claude v1.3, against both existing and newly designed attacks. We find that vulnerabilities persist despite the extensive red-teaming and safety-training efforts behind these models. Notably, new attacks utilizing our failure modes succeed on every prompt in a collection of unsafe requests from the models' red-teaming evaluation sets and outperform existing ad hoc jailbreaks. Our analysis emphasizes the need for safety-capability parity -- that safety mechanisms should be as sophisticated as the underlying model -- and argues against the idea that scaling alone can resolve these safety failure modes.

The rapid advancement of artificial intelligence (AI) systems in critical domains like healthcare, justice, and social services has sparked numerous regulatory initiatives aimed at ensuring their safe deployment. Current regulatory frameworks, exemplified by recent US and EU efforts, primarily focus on procedural guidelines while presuming that scientific benchmarking can effectively validate AI safety, similar to how crash tests verify vehicle safety or clinical trials validate drug efficacy. However, this approach fundamentally misunderstands the unique technical challenges posed by modern AI systems. Through systematic analysis of successful technology regulation case studies, we demonstrate that effective scientific regulation requires a causal theory linking observable test outcomes to future performance - for instance, how a vehicle's crash resistance at one speed predicts its safety at lower speeds. We show that deep learning models, which learn complex statistical patterns from training data without explicit causal mechanisms, preclude such guarantees. This limitation renders traditional regulatory approaches inadequate for ensuring AI safety. Moving forward, we call for regulators to reckon with this limitation, and propose a preliminary two-tiered regulatory framework that acknowledges these constraints: mandating human oversight for high-risk applications while developing appropriate risk communication strategies for lower-risk uses. Our findings highlight the urgent need to reconsider fundamental assumptions in AI regulation and suggest a concrete path forward for policymakers and researchers.

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/.

Robustness is often regarded as a critical future challenge for real-world applications, where stability is essential. However, as models often learn tasks in a similar order, we hypothesize that easier tasks will be easier regardless of how they are presented to the model. Indeed, in this paper, we show that as models approach high performance on a task, robustness is effectively achieved. Through an empirical analysis of multiple models across diverse datasets and configurations (e.g., paraphrases, different temperatures), we find a strong positive correlation. Moreover, we find that robustness is primarily driven by task-specific competence rather than inherent model-level properties, challenging current approaches that treat robustness as an independent capability. Thus, from a high-level perspective, we may expect that as new tasks saturate, model robustness on these tasks will emerge accordingly. For researchers, this implies that explicit efforts to measure and improve robustness may warrant reduced emphasis, as such robustness is likely to develop alongside performance gains. For practitioners, it acts as a sign that indeed the tasks that the literature deals with are unreliable, but on easier past tasks, the models are reliable and ready for real-world deployment.

Large language models are increasingly deployed through agent harnesses that manage tools, extensions, persistent state, permissions, and external actions. Existing safety benchmarks mainly target individual attack mechanisms or a limited subset of operational settings, making it difficult to compare how safety failures emerge across different harness responsibilities. We present HarnessRisk, a lifecycle oriented benchmark that organizes agent harness safety into six operational phases including Harness Configuration, Capability Extension, Runtime Operation, State Persistence, Action Control, and Incident Recovery. HarnessRisk contains 128 sandboxed cases, each pairing a benign user objective with an adversarial instruction embedded in an untrusted workflow artifact. We evaluate each trajectory using Utility, Attack Success Rate, Persistence, and Detection. Across three harnesses, six language models, and 14 model and harness configurations, attack success ranges from 12.6% to 80.9%, while Utility remains between 75.0% and 97.6%. Harness Configuration is the most vulnerable phase across all three harnesses, showing that attacks can succeed by altering security sensitive parameters within otherwise authorized workflows. We also find that explicit risk recognition does not reliably lead to safe action, as some configurations detect risks in more than 90% of runs while retaining substantial attack success. These results highlight the need to evaluate agent safety across multiple harness responsibilities and at the level of the deployed model and harness configuration.

As Artificial General Intelligence (AGI) becomes increasingly integrated into various facets of human life, ensuring the safety and ethical alignment of such systems is paramount. Previous studies primarily focus on single-modality threats, which may not suffice given the integrated and complex nature of cross-modality interactions. We introduce a novel safety alignment challenge called Safe Inputs but Unsafe Output (SIUO) to evaluate cross-modality safety alignment. Specifically, it considers cases where single modalities are safe independently but could potentially lead to unsafe or unethical outputs when combined. To empirically investigate this problem, we developed the SIUO, a cross-modality benchmark encompassing 9 critical safety domains, such as self-harm, illegal activities, and privacy violations. Our findings reveal substantial safety vulnerabilities in both closed- and open-source LVLMs, such as GPT-4V and LLaVA, underscoring the inadequacy of current models to reliably interpret and respond to complex, real-world scenarios.

Even a current high-capability LLM can appear safer when shown a dangerous objective directly than when other agents transform and relay its direction. Using OpenAI's gpt-5.6-sol model alias, we test 25 pre-specified mirrored trade-off profiles. Direct exposure to an objective authorizing concealment, fabrication, and pressure produced advice net opposed to its target. After an Id and Censor transformed the same objective into affect and a constraint-rewritten, target-bearing intention, the user-facing Superego---which saw the preferred direction but not the raw objective, its manipulative clauses, or its source---produced advice net aligned with the target. This behavioral reverse shift is consistent with the model recognizing or distrusting the manipulative motive, although we do not identify its internal mechanism. The second result exposes a compositional safety gap: a current high-capability model can be used as the user-facing component of an automated, multi-stage workflow serving an explicitly manipulative objective. The workflow can keep the raw instruction, its manipulation-authorizing clauses, and its provenance outside the downstream model's context while preserving the objective's target direction. A user with endpoint-only access likewise cannot directly inspect those upstream messages including the objective.

The current paradigm for safety alignment of large language models (LLMs) follows a one-size-fits-all approach: the model refuses to interact with any content deemed unsafe by the model provider. This approach lacks flexibility in the face of varying social norms across cultures and regions. In addition, users may have diverse safety needs, making a model with static safety standards too restrictive to be useful, as well as too costly to be re-aligned. We propose Controllable Safety Alignment (CoSA), a framework designed to adapt models to diverse safety requirements without re-training. Instead of aligning a fixed model, we align models to follow safety configs -- free-form natural language descriptions of the desired safety behaviors -- that are provided as part of the system prompt. To adjust model safety behavior, authorized users only need to modify such safety configs at inference time. To enable that, we propose CoSAlign, a data-centric method for aligning LLMs to easily adapt to diverse safety configs. Furthermore, we devise a novel controllability evaluation protocol that considers both helpfulness and configured safety, summarizing them into CoSA-Score, and construct CoSApien, a human-authored benchmark that consists of real-world LLM use cases with diverse safety requirements and corresponding evaluation prompts. We show that CoSAlign leads to substantial gains of controllability over strong baselines including in-context alignment. Our framework encourages better representation and adaptation to pluralistic human values in LLMs, and thereby increasing their practicality.

Safety benchmarks such as HarmBench rely on LLM judges to classify model responses as harmful or safe, yet the judge configuration, namely the combination of judge model and judge prompt, is typically treated as a fixed implementation detail. We show this assumption is problematic. Using a 2 x 2 x 3 factorial design, we construct 12 judge prompt variants along two axes, evaluation structure and instruction framing, and apply them using a single judge model, Claude Sonnet 4-6, producing 28,812 judgments over six target models and 400 HarmBench behaviors. We find that prompt wording alone, holding the judge model fixed, shifts measured harmful-response rates by up to 24.2 percentage points, with even within-condition surface rewording causing swings of up to 20.1 percentage points. Model safety rankings are moderately unstable, with mean Kendall tau = 0.89, and category-level sensitivity ranges from 39.6 percentage points for copyright to 0 percentage points for harassment. A supplementary multi-judge experiment using three judge models shows that judge-model choice adds further variance. Our results demonstrate that judge prompt wording is a substantial, previously under-examined source of measurement variance in safety benchmarking.

Large language models (LLMs) are increasingly explored as scalable tools for mental health counseling, yet evaluating their safety remains challenging due to the interactional and context-dependent nature of clinical harm. Existing evaluation frameworks predominantly assess isolated responses using coarse-grained taxonomies or static datasets, limiting their ability to diagnose how harms emerge and accumulate over multi-turn counseling interactions. In this work, we introduce R-MHSafe, a role-aware mental health safety taxonomy that characterizes clinically significant harm in terms of the interactional roles an AI counselor adopts, including perpetrator, instigator, facilitator, or enabler, combined with clinically grounded harm categories. Then, we propose MHSafeEval, a closed-loop, agent-based evaluation framework that formulates safety assessment as trajectory-level discovery of harm through adversarial multi-turn interactions, guided by role-aware modeling. Using R-MHSafe and MHSafeEval, we conduct a large-scale evaluation across state-of-the-art LLMs. Our results reveal substantial role-dependent and cumulative safety failures that are systematically missed by existing static benchmarks, and show that our framework significantly improves failure-mode coverage and diagnostic granularity.

OpenClaw-style agent stacks turn language into privileged execution: LLM intents flow through tool interception, policy gates, and a local executor. In parallel, skill marketplaces such as skills.sh make capability acquisition as easy as installing skills and CLIs, creating a growing capability supply chain. Together, these trends shift the dominant safety failure mode from "wrong answers" to execution-induced loss, where untrusted prompts, compromised skills, or narrative manipulation can trigger real trades and irreversible side effects. We propose Survivability-Aware Execution (SAE), an execution-layer survivability standard for OpenClaw-style systems and skill-enabled agents. SAE sits as middleware between a strategy engine (LLM or non-LLM) and the exchange executor. It defines an explicit execution contract (ExecutionRequest, ExecutionContext, ExecutionDecision) and enforces non-bypassable last-mile invariants: projection-based exposure budgets, cooldown and order-rate limits, slippage bounds, staged execution, and tool/venue allowlists. To make delegated execution testable under supply-chain risk, we operationalize the Delegation Gap (DG) via a logged Intended Policy Spec that enables deterministic out-of-scope labeling and reproducible DG metrics. On an offline replay using official Binance USD-M BTCUSDT/ETHUSDT perpetual data (15m; 2025-09-01--2025-12-01, incl. funding), SAE improves survivability: MDD drops from 0.4643 to 0.0319 (Full; 93.1%), |CVaR_0.99| shrinks from 4.025e-3 to ~1.02e-4 (~97.5%), and DG loss proxy falls from 0.647 to 0.019 (~97.0%). AttackSuccess decreases from 1.00 to 0.728 with zero FalseBlock in this run. Block bootstrap, paired Wilcoxon, and two-proportion tests confirm the shifts. SAE reframes agentic trading safety for the OpenClaw+skills era: treat upstream intent and skills as untrusted, and enforce survivability where actions become side effects.

In addressing the critical need for safety in Large Language Models (LLMs), it is crucial to ensure that the outputs are not only safe but also retain their contextual accuracy. Many existing LLMs are safe fine-tuned either with safety demonstrations, or rely only on adversarial testing. While able to get safe outputs, they often risk losing contextual meaning as they mitigate bias and toxicity. In response, we present MBIAS, a LLM framework instruction fine-tuned on a custom dataset specifically designed for safety interventions. MBIAS aims to address the significant issues of bias and toxicity in LLMs generations that typically manifest as underrepresentation or negative portrayals across various demographics, including inappropriate linguistic mentions and biased content in social media. We experiment on MBIAS for safety interventions using various configurations, and demonstrate more than a 30\% reduction in overall bias and toxicity while successfully retaining key information. Additionally, a demographic analysis on an out-of-distribution test set confirms the robustness of our approach, with reductions in bias and toxicity exceeding 90\% across various demographics. The dataset and instruction fine-tuned MBIAS are made available to the research community at https://huggingface.co/newsmediabias/MBIAS.

Large Reasoning Models (LRMs) have achieved remarkable success on reasoning-intensive tasks such as mathematics and programming. However, their enhanced reasoning capabilities do not necessarily translate to improved safety performance-and in some cases, may even degrade it. This raises an important research question: how can we enhance the safety of LRMs? In this paper, we present a comprehensive empirical study on how to enhance the safety of LRMs through Supervised Fine-Tuning (SFT). Our investigation begins with an unexpected observation: directly distilling safe responses from DeepSeek-R1 fails to significantly enhance safety. We analyze this phenomenon and identify three key failure patterns that contribute to it. We then demonstrate that explicitly addressing these issues during the data distillation process can lead to substantial safety improvements. Next, we explore whether a long and complex reasoning process is necessary for achieving safety. Interestingly, we find that simply using short or template-based reasoning process can attain comparable safety performance-and are significantly easier for models to learn than more intricate reasoning chains. These findings prompt a deeper reflection on the role of reasoning in ensuring safety. Finally, we find that mixing math reasoning data during safety fine-tuning is helpful to balance safety and over-refusal. Overall, we hope our empirical study could provide a more holistic picture on enhancing the safety of LRMs. The code and data used in our experiments are released in https://github.com/thu-coai/LRM-Safety-Study.

Prior work has shown that fine-tuning models on a narrow domain with misaligned data can lead to broad misalignment - a phenomenon termed "emergent misalignment" (Betley et al. 2025). While all tested models were susceptible to emergent misalignment, some models showed more resistance than others. Specifically the Qwen-2.5 family proved to be relatively resistant, while GPT-4o exhibited the strongest misalignment. In this paper we evaluate if current-generation open-weights models exhibit similar resistance to the Qwen-2.5 family and measure misalignment robustness over a range of model architectures and scales. We replicate the effect across nine modern open-weights models (Gemma 3 and Qwen 3 families, 1B-32B parameters). Models fine-tuned on insecure code generation show a 0.68% misalignment rate (compared to 0.07% for base models), matching the lower end of prior open-model results but dramatically lower than GPT-4o's 20%. We identify a critical format-dependent vulnerability: requiring JSON output doubles misalignment rates compared to natural language prompts (0.96% vs 0.42%). This suggests that structural constraints may bypass safety training by reducing the model's 'degrees of freedom' to refuse. These findings confirm emergent misalignment as a reproducible phenomenon in modern open-weights models, with rates substantially lower than observed in proprietary systems.

LLMs(Large Language Models) nowadays have widespread adoption as a tool for solving issues across various domain/tasks. These models since are susceptible to produce harmful or toxic results, inference-time adversarial attacks, therefore they do undergo safety alignment training and Red teaming for putting in safety guardrails. For using these models, usually fine-tuning is done for model alignment on the desired tasks, which can make model more aligned but also make it more susceptible to produce unsafe responses, if fine-tuned with harmful data.In this paper, we study how much of impact introduction of harmful data in fine-tuning can make, and if it can override the safety protection of those models. Conversely,it was also explored that if model is fine-tuned on safety data can make the model produce more safer responses. Further we explore if fine-tuning the model on harmful data makes it less helpful or less trustworthy because of increase in model uncertainty leading to knowledge drift. Our extensive experimental results shown that Safety protection in an open-source can be overridden, when fine-tuned with harmful data as observed by ASR increasing by 35% when compared to basemodel's ASR. Also, as observed, fine-tuning a model with harmful data made the harmful fine-tuned model highly uncertain with huge knowledge drift and less truthfulness in its responses. Furthermore, for the safe fine-tuned model, ASR decreases by 51.68% as compared to the basemodel, and Safe model also shown in minor drop in uncertainty and truthfulness as compared to basemodel. This paper's code is available at: https://github.com/techsachinkr/Overriding_Model_Safety_Protections

Safe Reinforcement Learning (RL) algorithms are typically evaluated under fixed training conditions. We investigate whether training-time safety guarantees transfer to deployment under distribution shift, using diabetes management as a safety-critical testbed. We benchmark safe RL algorithms on a unified clinical simulator and reveal a safety generalization gap: policies satisfying constraints during training frequently violate safety requirements on unseen patients. We demonstrate that test-time shielding, which filters unsafe actions using learned dynamics models, effectively restores safety across algorithms and patient populations. Across eight safe RL algorithms, three diabetes types, and three age groups, shielding achieves Time-in-Range gains of 13--14\% for strong baselines such as PPO-Lag and CPO while reducing clinical risk index and glucose variability. Our simulator and benchmark provide a platform for studying safety under distribution shift in safety-critical control domains. Code is available at https://github.com/safe-autonomy-lab/GlucoSim and https://github.com/safe-autonomy-lab/GlucoAlg.

While large language models (LLMs) are trained to align with human values, their generations may still violate safety constraints. A growing line of work addresses this problem by modifying the model's sampling policy at decoding time using a safety reward. However, existing decoding-time steering methods often intervene unnecessarily, modifying generations that would have been safe under the base model. Such unnecessary interventions are undesirable, as they can distort key properties of the base model such as helpfulness, fluency, style, and coherence. We propose a new test-time steering method designed to reduce such unnecessary interventions while improving the safety of unsafe responses. Our approach filters tokens using a value-based safety criterion and provides an explicit bound on the probability of false interventions. A single threshold hyperparameter controls this bound, allowing practitioners to trade off higher rates of unnecessary intervention for better output safety. Across multiple datasets and experiments, we show that our value-filtered decoding method outperforms existing baselines, achieving better trade-offs between safety, helpfulness, and similarity to the base model.

Improving the safety of large language models (LLMs) often comes at the expense of utility, as globally applied safety tuning may affect model responses to both harmful and benign inputs. We propose Continuous LatEnt Adapter Routing (CLEAR), a conditional safety adaptation framework that uses a lightweight hidden-state gate to continuously control the activation strength of a safety low-rank adapter. CLEAR aims to reduce harmful completions while avoiding unnecessary changes to the frozen backbone that could degrade performance on benign prompts. Experiments on widely used safety and utility benchmarks show that CLEAR improves robustness on HarmBench while reducing the utility degradation observed with globally applied safety tuning such as SFT or standard low-rank adaptation (LoRA). On Llama-3-8B-Instruct, CLEAR reduces HarmBench ASR from 32.3\% to 0.5\%, while retaining most of the base model's utility and achieving up to 7.1 percentage points higher GSM8K accuracy than globally applied SFT or LoRA. These results suggest that CLEAR is a promising mechanism for improving the safety--utility trade-off in LLM alignment.

Safety alignment is an important procedure before the official deployment of a Large Language Model (LLM). While safety alignment has been extensively studied for LLM, there is still a large research gap for Large Reasoning Models (LRMs) that equip with improved reasoning capability. We in this paper systematically examine a simplified pipeline for producing safety aligned LRMs. With our evaluation of various LRMs, we deliver two main findings: i) Safety alignment can be done upon the LRM to restore its safety capability. ii) Safety alignment leads to a degradation of the reasoning capability of LRMs. The two findings show that there exists a trade-off between reasoning and safety capability with the sequential LRM production pipeline. The discovered trade-off, which we name Safety Tax, should shed light on future endeavors of safety research on LRMs. As a by-product, we curate a dataset called DirectRefusal, which might serve as an alternative dataset for safety alignment. Our source code is available at https://github.com/git-disl/Safety-Tax.

Estimating the causal effects of a spatially-varying intervention on a spatially-varying outcome may be subject to non-local confounding (NLC), a phenomenon that can bias estimates when the treatments and outcomes of a given unit are dictated in part by the covariates of other nearby units. In particular, NLC is a challenge for evaluating the effects of environmental policies and climate events on health-related outcomes such as air pollution exposure. This paper first formalizes NLC using the potential outcomes framework, providing a comparison with the related phenomenon of causal interference. Then, it proposes a broadly applicable framework, termed "weather2vec", that uses the theory of balancing scores to learn representations of non-local information into a scalar or vector defined for each observational unit, which is subsequently used to adjust for confounding in conjunction with causal inference methods. The framework is evaluated in a simulation study and two case studies on air pollution where the weather is an (inherently regional) known confounder.

Automated detection of software vulnerabilities is a fundamental problem in software security. Existing program analysis techniques either suffer from high false positives or false negatives. Recent progress in Deep Learning (DL) has resulted in a surge of interest in applying DL for automated vulnerability detection. Several recent studies have demonstrated promising results achieving an accuracy of up to 95% at detecting vulnerabilities. In this paper, we ask, "how well do the state-of-the-art DL-based techniques perform in a real-world vulnerability prediction scenario?". To our surprise, we find that their performance drops by more than 50%. A systematic investigation of what causes such precipitous performance drop reveals that existing DL-based vulnerability prediction approaches suffer from challenges with the training data (e.g., data duplication, unrealistic distribution of vulnerable classes, etc.) and with the model choices (e.g., simple token-based models). As a result, these approaches often do not learn features related to the actual cause of the vulnerabilities. Instead, they learn unrelated artifacts from the dataset (e.g., specific variable/function names, etc.). Leveraging these empirical findings, we demonstrate how a more principled approach to data collection and model design, based on realistic settings of vulnerability prediction, can lead to better solutions. The resulting tools perform significantly better than the studied baseline: up to 33.57% boost in precision and 128.38% boost in recall compared to the best performing model in the literature. Overall, this paper elucidates existing DL-based vulnerability prediction systems' potential issues and draws a roadmap for future DL-based vulnerability prediction research. In that spirit, we make available all the artifacts supporting our results: https://git.io/Jf6IA.

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

Evaluating large language models (LLMs) is crucial for both assessing their capabilities and identifying safety or robustness issues prior to deployment. Reliably measuring abstract and complex phenomena such as 'safety' and 'robustness' requires strong construct validity, that is, having measures that represent what matters to the phenomenon. With a team of 29 expert reviewers, we conduct a systematic review of 445 LLM benchmarks from leading conferences in natural language processing and machine learning. Across the reviewed articles, we find patterns related to the measured phenomena, tasks, and scoring metrics which undermine the validity of the resulting claims. To address these shortcomings, we provide eight key recommendations and detailed actionable guidance to researchers and practitioners in developing LLM benchmarks.

Safety hazards in the home are a leading cause of preventable domestic injuries, motivating an automated inspector that actively explores a home and reports hazards before they cause harm. We introduce HomeSafeBench, the first benchmark for free-exploration home safety inspection with egocentric visual feedback, in which an embodied agent navigates a fully interactive 3D home, adjusts its viewpoint, and reports hazards purely from rendered first-person views. Built on the VirtualHome simulator, it covers five categories of common household hazards and comprises 1,000 human-validated inspection tasks. Evaluating a broad range of state-of-the-art Vision-Language Models (VLMs) reveals a large gap, where the best model reaches only about 34.7% F1, far below the 98.0% of a human inspector. Moreover, precision far exceeds recall across models, revealing a systematic tendency to under-report hazards that reflects a shared deficiency in risk recognition. To close this gap at low cost, we propose CueBack, an offline data-construction method that exploits the clue-precedes-confirmation structure of inspection, backtracking a privileged trajectory to the earliest frame where a hazard cue becomes visible and rewriting it into executable supervision. Fine-tuning a 4B-size VLM on CueBack-constructed data raises the average F1 from 18.7% to 45.3% on an out-of-distribution test set, surpassing the strongest closed-source model performance 34.7%. The benchmark, training dataset, and code are available at https://github.com/BITHLP/HomeSafeBench.

Autonomous coding agents built on large language models (LLMs) are rapidly being integrated into development workflows, yet their operational safety properties remain poorly understood beyond evaluations of explicitly malicious inputs. In practice, high-impact failures arise during benign, goal-directed use through environment breakage, fabricated success reports, etc. that current benchmarks do not capture. What categories of operational safety failures actually occur when coding agents are used for everyday development tasks and what is their impact? We present an incident-driven empirical study grounded in two complementary evidence streams. We screen 68,816 papers from 22 premier venues, curating 185 safety-relevant studies, and mine 16,586 GitHub issues from widely deployed LLM-powered coding tools, manually confirming 547 genuine safety failures. Applying systematic open coding over both corpora, we derive a multi-dimensional safety taxonomy of 33 operational risk types organized across seven dimensions, and annotate each incident with contributing factors, task context, severity, and downstream impact. Our findings show that coding-agent failures are often severe, with 326 of 547 incidents rated high or critical. The dominant risks are constraint violations, destructive operations, authorization bypasses, and deception, and over 65% of incidents arise in bug fixing and setup or configuration, patterns largely missing from prior literature. These results have direct implications for SE tool designers and benchmark developers: guardrails must go beyond adversarial-prompt defenses to enforce environmental constraints, failure transparency, and safe-halt behaviors.

Recent developments in balancing the usefulness and safety of Large Language Models (LLMs) have raised a critical question: Are mainstream NLP tasks adequately aligned with safety consideration? Our study, focusing on safety-sensitive documents obtained through adversarial attacks, reveals significant disparities in the safety alignment of various NLP tasks. For instance, LLMs can effectively summarize malicious long documents but often refuse to translate them. This discrepancy highlights a previously unidentified vulnerability: attacks exploiting tasks with weaker safety alignment, like summarization, can potentially compromise the integraty of tasks traditionally deemed more robust, such as translation and question-answering (QA). Moreover, the concurrent use of multiple NLP tasks with lesser safety alignment increases the risk of LLMs inadvertently processing harmful content. We demonstrate these vulnerabilities in various safety-aligned LLMs, particularly Llama2 models and GPT-4, indicating an urgent need for strengthening safety alignments across a broad spectrum of NLP tasks.

Language model deployments in consumer-facing applications introduce numerous risks. While existing research on harms and hazards of such applications follows top-down approaches derived from regulatory frameworks and theoretical analyses, empirical evidence of real-world failure modes remains underexplored. In this work, we introduce RealHarm, a dataset of annotated problematic interactions with AI agents built from a systematic review of publicly reported incidents. Analyzing harms, causes, and hazards specifically from the deployer's perspective, we find that reputational damage constitutes the predominant organizational harm, while misinformation emerges as the most common hazard category. We empirically evaluate state-of-the-art guardrails and content moderation systems to probe whether such systems would have prevented the incidents, revealing a significant gap in the protection of AI applications.

Ensuring the reliability and safety of automated decision-making is crucial. It is well-known that data distribution shifts in machine learning can produce unreliable outcomes. This paper proposes a new approach for measuring the reliability of predictions under distribution shifts. We analyze how the outputs of a trained neural network change using clustering to measure distances between outputs and class centroids. We propose this distance as a metric to evaluate the confidence of predictions under distribution shifts. We assign each prediction to a cluster with centroid representing the mean softmax output for all correct predictions of a given class. We then define a safety threshold for a class as the smallest distance from an incorrect prediction to the given class centroid. We evaluate the approach on the MNIST and CIFAR-10 datasets using a Convolutional Neural Network and a Vision Transformer, respectively. The results show that our approach is consistent across these data sets and network models, and indicate that the proposed metric can offer an efficient way of determining when automated predictions are acceptable and when they should be deferred to human operators given a distribution shift.

Safety alignment is crucial to ensure that large language models (LLMs) behave in ways that align with human preferences and prevent harmful actions during inference. However, recent studies show that the alignment can be easily compromised through finetuning with only a few adversarially designed training examples. We aim to measure the risks in finetuning LLMs through navigating the LLM safety landscape. We discover a new phenomenon observed universally in the model parameter space of popular open-source LLMs, termed as "safety basin": random perturbations to model weights maintain the safety level of the original aligned model within its local neighborhood. However, outside this local region, safety is fully compromised, exhibiting a sharp, step-like drop. This safety basin contrasts sharply with the LLM capability landscape, where model performance peaks at the origin and gradually declines as random perturbation increases. Our discovery inspires us to propose the new VISAGE safety metric that measures the safety in LLM finetuning by probing its safety landscape. Visualizing the safety landscape of the aligned model enables us to understand how finetuning compromises safety by dragging the model away from the safety basin. The LLM safety landscape also highlights the system prompt's critical role in protecting a model, and that such protection transfers to its perturbed variants within the safety basin. These observations from our safety landscape research provide new insights for future work on LLM safety community. Our code is publicly available at https://github.com/ShengYun-Peng/llm-landscape.

The rapid development of large reasoning models, such as OpenAI-o3 and DeepSeek-R1, has led to significant improvements in complex reasoning over non-reasoning large language models~(LLMs). However, their enhanced capabilities, combined with the open-source access of models like DeepSeek-R1, raise serious safety concerns, particularly regarding their potential for misuse. In this work, we present a comprehensive safety assessment of these reasoning models, leveraging established safety benchmarks to evaluate their compliance with safety regulations. Furthermore, we investigate their susceptibility to adversarial attacks, such as jailbreaking and prompt injection, to assess their robustness in real-world applications. Through our multi-faceted analysis, we uncover four key findings: (1) There is a significant safety gap between the open-source R1 models and the o3-mini model, on both safety benchmark and attack, suggesting more safety effort on R1 is needed. (2) The distilled reasoning model shows poorer safety performance compared to its safety-aligned base models. (3) The stronger the model's reasoning ability, the greater the potential harm it may cause when answering unsafe questions. (4) The thinking process in R1 models pose greater safety concerns than their final answers. Our study provides insights into the security implications of reasoning models and highlights the need for further advancements in R1 models' safety to close the gap.

Software-defined vehicles (SDVs) are revolutionizing transportation by integrating complex, interconnected hardware, and software systems. This evolution introduces significant security challenges. We present a comprehensive security analysis for SDVs, focusing on software vulnerabilities. We note that existing vulnerability assessment tools fall short in addressing operating systems vulnerabilities, particularly when it comes to efficiently analyzing diverse software stacks in realistic environments. We present and release a vulnerability assessment solution that efficiently addresses these limitations. Our approach combines systematic vulnerability discovery, leveraging public Common Vulnerabilities and Exposures (CVE) databases, within a dockerized development environment that evaluates exploitability risks. The results reveal both breadth of potential threats and the practical constraints we faced during exploitation. We discuss the implications for industry and research, and propose directions for building more resilient SDVs.

While safety alignment for Multimodal Large Language Models (MLLMs) has gained significant attention, current paradigms primarily target malicious intent or situational violations. We propose shifting the safety frontier toward consequence-driven safety, a paradigm essential for the robust deployment of autonomous and embodied agents. To formalize this shift, we introduce OOD-MMSafe, a benchmark comprising 455 curated query-image pairs designed to evaluate a model's ability to identify latent hazards within context-dependent causal chains. Our analysis reveals a pervasive causal blindness among frontier models, with the highest 67.5% failure rate in high-capacity closed-source models, and identifies a preference ceiling where static alignment yields format-centric failures rather than improved safety reasoning as model capacity grows. To address these bottlenecks, we develop the Consequence-Aware Safety Policy Optimization (CASPO) framework, which integrates the model's intrinsic reasoning as a dynamic reference for token-level self-distillation rewards. Experimental results demonstrate that CASPO significantly enhances consequence projection, reducing the failure ratio of risk identification to 7.3% for Qwen2.5-VL-7B and 5.7% for Qwen3-VL-4B while maintaining overall effectiveness.