Daily Papers

Reward models (RMs) are essential for aligning Large Language Models (LLMs) with human preferences. However, they often struggle with capturing complex human preferences and generalizing to unseen data. To address these challenges, we introduce Energy-Based Reward Model (EBRM), a lightweight post-hoc refinement framework that enhances RM robustness and generalization. EBRM models the reward distribution explicitly, capturing uncertainty in human preferences and mitigating the impact of noisy or misaligned annotations. It achieves this through conflict-aware data filtering, label-noise-aware contrastive training, and hybrid initialization. Notably, EBRM enhances RMs without retraining, making it computationally efficient and adaptable across different models and tasks. Empirical evaluations on RM benchmarks demonstrate significant improvements in both robustness and generalization, achieving up to a 5.97% improvement in safety-critical alignment tasks compared to standard RMs. Furthermore, reinforcement learning experiments confirm that our refined rewards enhance alignment quality, effectively delaying reward hacking. These results demonstrate our approach as a scalable and effective enhancement for existing RMs and alignment pipelines. The code is available at EBRM.

Fine-tuning is the primary mechanism for adapting foundation models to downstream tasks; however, standard approaches largely optimize task objectives in isolation and do not account for secondary yet critical alignment objectives (e.g., safety and hallucination avoidance). As a result, downstream fine-tuning can degrade alignment and fail to correct pre-existing misaligned behavior. We propose an alignment-aware fine-tuning framework that integrates feedback from an external alignment signal through policy-gradient-based regularization. Our method introduces an adaptive gating mechanism that dynamically balances supervised and alignment-driven gradients on a per-sample basis, prioritizing uncertain or misaligned cases while allowing well-aligned examples to follow standard supervised updates. The framework further learns abstention behavior for fully misaligned inputs, incorporating conservative responses directly into the fine-tuned model. Experiments on general and domain-specific instruction-tuning benchmarks demonstrate consistent reductions in harmful and hallucinated outputs without sacrificing downstream task performance. Additional analyses show robustness to adversarial fine-tuning, prompt-based attacks, and unsafe initializations, establishing adaptively gated alignment optimization as an effective approach for alignment-preserving and alignment-recovering model adaptation.

Current safety evaluations for LLM-driven agents primarily focus on atomic harms, failing to address sophisticated threats where malicious intent is concealed or diluted within complex tasks. We address this gap with a two-dimensional analysis of agent safety brittleness under the orthogonal pressures of intent concealment and task complexity. To enable this, we introduce OASIS (Orthogonal Agent Safety Inquiry Suite), a hierarchical benchmark with fine-grained annotations and a high-fidelity simulation sandbox. Our findings reveal two critical phenomena: safety alignment degrades sharply and predictably as intent becomes obscured, and a "Complexity Paradox" emerges, where agents seem safer on harder tasks only due to capability limitations. By releasing OASIS and its simulation environment, we provide a principled foundation for probing and strengthening agent safety in these overlooked dimensions.

Large Language Models (LLMs) are increasingly employed as automated evaluators to assess the safety of generated content, yet their reliability in this role remains uncertain. This study evaluates a diverse set of 11 LLM judge models across critical safety domains, examining three key aspects: self-consistency in repeated judging tasks, alignment with human judgments, and susceptibility to input artifacts such as apologetic or verbose phrasing. Our findings reveal that biases in LLM judges can significantly distort the final verdict on which content source is safer, undermining the validity of comparative evaluations. Notably, apologetic language artifacts alone can skew evaluator preferences by up to 98\%. Contrary to expectations, larger models do not consistently exhibit greater robustness, while smaller models sometimes show higher resistance to specific artifacts. To mitigate LLM evaluator robustness issues, we investigate jury-based evaluations aggregating decisions from multiple models. Although this approach both improves robustness and enhances alignment to human judgements, artifact sensitivity persists even with the best jury configurations. These results highlight the urgent need for diversified, artifact-resistant methodologies to ensure reliable safety assessments.

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.

The widespread adoption of Large Language Models (LLMs) for code generation, exemplified by GitHub CopilotA coding extension powered by a Code-LLM to assist in code completion tasks surpassing a million users, highlights the transformative potential of these tools in improving developer productivity. However, this rapid growth also underscores critical concerns regarding the quality, safety, and reliability of the code they generate. As Code-LLMs evolve, they face significant challenges, including the diminishing returns of model scaling and the scarcity of new, high-quality training data. To address these issues, this paper introduces Adversarial Knowledge Distillation (AKD), a novel approach that leverages adversarially generated synthetic datasets to distill the capabilities of larger models into smaller, more efficient ones. By systematically stress-testing and refining the reasoning capabilities of Code-LLMs, AKD provides a framework for enhancing model robustness, reliability, and security while improving their parameter-efficiency. We believe this work represents a critical step toward ensuring dependable automated code generation within the constraints of existing data and the cost-efficiency of model execution.

Ensuring the safety and value alignment of large language models (LLMs) is critical for their deployment. Current alignment efforts primarily target explicit risks such as bias, hate speech, and violence. However, they often fail to address deeper, domain-specific implicit risks and lack a flexible, generalizable framework applicable across diverse specialized fields. Hence, we proposed MENTOR: A MEtacognition-driveN self-evoluTion framework for uncOvering and mitigating implicit Risks in LLMs on Domain Tasks. To address the limitations of labor-intensive human evaluation, we introduce a novel metacognitive self-assessment tool. This enables LLMs to reflect on potential value misalignments in their responses using strategies like perspective-taking and consequential thinking. We also release a supporting dataset of 9,000 risk queries spanning education, finance, and management to enhance domain-specific risk identification. Subsequently, based on the outcomes of metacognitive reflection, the framework dynamically generates supplementary rule knowledge graphs that extend predefined static rule trees. This enables models to actively apply validated rules to future similar challenges, establishing a continuous self-evolution cycle that enhances generalization by reducing maintenance costs and inflexibility of static systems. Finally, we employ activation steering during inference to guide LLMs in following the rules, a cost-effective method to robustly enhance enforcement across diverse contexts. Experimental results show MENTOR's effectiveness: In defensive testing across three vertical domains, the framework substantially reduces semantic attack success rates, enabling a new level of implicit risk mitigation for LLMs. Furthermore, metacognitive assessment not only aligns closely with baseline human evaluators but also delivers more thorough and insightful analysis of LLMs value alignment.

Low-rank adaptation (LoRA) has become a standard tool for efficiently fine-tuning large language models (LLMs). Yet, even minor LoRA updates can induce alignment drift, weakening safety and behavioral constraints through entangled parameter changes. To address this, we propose AlignGuard-LoRA (AGL), a principled framework for preserving alignment during finetuning. AGL introduces several key components: a primary task loss for supervision, Fisher Information Matrix-based regularization to restrict updates in alignment-sensitive subspaces, and task-specific regularization to stabilize the integration of new knowledge. We further introduce collision-aware regularization, blending Riemannian overlap -- which penalizes coordinate-wise interference -- and geodesic separation -- which encourages disjoint update geometry. We curate DriftCaps, a targeted diagnostic benchmark of safe and unsafe prompts designed to quantify alignment drift and safety degradation. Empirical evaluations show that AGL mitigates alignment drift by up to 50% on safety-critical benchmarks without degrading downstream task performance. Comprehensive ablation confirms that each component contributes distinctly to preserving latent safety behaviors. Finally, we derive and validate a scaling law for catastrophic forgetting, revealing that AGL flattens post-finetuning loss escalation while preserving adaptation dynamics. AGL is a structurally grounded refinement of LoRA, ensuring alignment preservation with minimal trade-offs. To encourage further exploration and development, we open-source our implementation.

Ensuring the safe alignment of large language models (LLMs) with human values is critical as they become integral to applications like translation and question answering. Current alignment methods struggle with dynamic user intentions and complex objectives, making models vulnerable to generating harmful content. We propose Safety Arithmetic, a training-free framework enhancing LLM safety across different scenarios: Base models, Supervised fine-tuned models (SFT), and Edited models. Safety Arithmetic involves Harm Direction Removal to avoid harmful content and Safety Alignment to promote safe responses. Additionally, we present NoIntentEdit, a dataset highlighting edit instances that could compromise model safety if used unintentionally. Our experiments show that Safety Arithmetic significantly improves safety measures, reduces over-safety, and maintains model utility, outperforming existing methods in ensuring safe content generation.

Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques includes principle-driven integration, but it faces challenges arising from the imprecision of manually crafted rules and inadequate risk perception in models without safety training. To address these, we introduce Guide-Align, a two-stage approach. Initially, a safety-trained model identifies potential risks and formulates specific guidelines for various inputs, establishing a comprehensive library of guidelines and a model for input-guidelines retrieval. Subsequently, the retrieval model correlates new inputs with relevant guidelines, which guide LLMs in response generation to ensure safe and high-quality outputs, thereby aligning with human values. An additional optional stage involves fine-tuning a model with well-aligned datasets generated through the process implemented in the second stage. Our method customizes guidelines to accommodate diverse inputs, thereby enhancing the fine-grainedness and comprehensiveness of the guideline library. Furthermore, it incorporates safety expertise from a safety-trained LLM through a lightweight retrieval model. We evaluate our approach on three benchmarks, demonstrating significant improvements in LLM security and quality. Notably, our fine-tuned model, Labrador, even at 13 billion parameters, outperforms GPT-3.5-turbo and surpasses GPT-4 in alignment capabilities.

Fine-tuning safety-aligned large language models (LLMs) can substantially compromise their safety. Previous approaches require many safety samples or calibration sets, which not only incur significant computational overhead during realignment but also lead to noticeable degradation in model utility. Contrary to this belief, we show that safety alignment can be fully recovered with only a single safety example, without sacrificing utility and at minimal cost. Remarkably, this recovery is effective regardless of the number of harmful examples used in fine-tuning or the size of the underlying model, and convergence is achieved within just a few epochs. Furthermore, we uncover the low-rank structure of the safety gradient, which explains why such efficient correction is possible. We validate our findings across five safety-aligned LLMs and multiple datasets, demonstrating the generality of our approach.

As large language models (LLMs) are increasingly deployed in high-stakes settings, the risk of generating harmful or toxic content remains a central challenge. Post-hoc alignment methods are brittle: once unsafe patterns are learned during pretraining, they are hard to remove. We present a data-centric pretraining framework that builds safety into the model from the start. Our contributions include: (i) a safety classifier trained on 10,000 GPT-4 labeled examples, used to filter 600B tokens; (ii) the largest synthetic safety dataset to date (100B tokens) generated via recontextualization of harmful web data; (iii) RefuseWeb and Moral Education datasets that convert harmful prompts into refusal dialogues and web-style educational material; (iv) Harmfulness-Tag annotations injected during pretraining to flag unsafe content and steer away inference from harmful generations; and (v) safety evaluations measuring base model behavior before instruction tuning. Our safety-pretrained models reduce attack success rates from 38.8% to 8.4% with no performance degradation on standard LLM safety benchmarks.

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.

Although AI systems have been applied in various fields and achieved impressive performance, their safety and reliability are still a big concern. This is especially important for safety-critical tasks. One shared characteristic of these critical tasks is their risk sensitivity, where small mistakes can cause big consequences and even endanger life. There are several factors that could be guidelines for the successful deployment of AI systems in sensitive tasks: (i) failure detection and out-of-distribution (OOD) detection; (ii) overfitting identification; (iii) uncertainty quantification for predictions; (iv) robustness to data perturbations. These factors are also challenges of current AI systems, which are major blocks for building safe and reliable AI. Specifically, the current AI algorithms are unable to identify common causes for failure detection. Furthermore, additional techniques are required to quantify the quality of predictions. All these contribute to inaccurate uncertainty quantification, which lowers trust in predictions. Hence obtaining accurate model uncertainty quantification and its further improvement are challenging. To address these issues, many techniques have been proposed, such as regularization methods and learning strategies. As vision and language are the most typical data type and have many open source benchmark datasets, this thesis will focus on vision-language data processing for tasks like classification, image captioning, and vision question answering. In this thesis, we aim to build a safeguard by further developing current techniques to ensure the accurate model uncertainty for safety-critical tasks.

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 alignment is critical for the ethical deployment of large language models (LLMs), guiding them to avoid generating harmful or unethical content. Current alignment techniques, such as supervised fine-tuning and reinforcement learning from human feedback, remain fragile and can be bypassed by carefully crafted adversarial prompts. Unfortunately, such attacks rely on trial and error, lack generalizability across models, and are constrained by scalability and reliability. This paper presents NeuroStrike, a novel and generalizable attack framework that exploits a fundamental vulnerability introduced by alignment techniques: the reliance on sparse, specialized safety neurons responsible for detecting and suppressing harmful inputs. We apply NeuroStrike to both white-box and black-box settings: In the white-box setting, NeuroStrike identifies safety neurons through feedforward activation analysis and prunes them during inference to disable safety mechanisms. In the black-box setting, we propose the first LLM profiling attack, which leverages safety neuron transferability by training adversarial prompt generators on open-weight surrogate models and then deploying them against black-box and proprietary targets. We evaluate NeuroStrike on over 20 open-weight LLMs from major LLM developers. By removing less than 0.6% of neurons in targeted layers, NeuroStrike achieves an average attack success rate (ASR) of 76.9% using only vanilla malicious prompts. Moreover, Neurostrike generalizes to four multimodal LLMs with 100% ASR on unsafe image inputs. Safety neurons transfer effectively across architectures, raising ASR to 78.5% on 11 fine-tuned models and 77.7% on five distilled models. The black-box LLM profiling attack achieves an average ASR of 63.7% across five black-box models, including the Google Gemini family.

Aligning large language models (LLMs) with human intentions has become a critical task for safely deploying models in real-world systems. While existing alignment approaches have seen empirical success, theoretically understanding how these methods affect model behavior remains an open question. Our work provides an initial attempt to theoretically analyze the learning dynamics of human preference alignment. We formally show how the distribution of preference datasets influences the rate of model updates and provide rigorous guarantees on the training accuracy. Our theory also reveals an intricate phenomenon where the optimization is prone to prioritizing certain behaviors with higher preference distinguishability. We empirically validate our findings on contemporary LLMs and alignment tasks, reinforcing our theoretical insights and shedding light on considerations for future alignment approaches. Disclaimer: This paper contains potentially offensive text; reader discretion is advised.

Vision Language Models (VLMs) are increasingly integrated into privacy-critical domains, yet existing evaluations of personally identifiable information (PII) leakage largely treat privacy as a static extraction task and ignore how a subject's online presence--the volume of their data available online--influences privacy alignment. We introduce PII-VisBench, a novel benchmark containing 4000 unique probes designed to evaluate VLM safety through the continuum of online presence. The benchmark stratifies 200 subjects into four visibility categories: high, medium, low, and zero--based on the extent and nature of their information available online. We evaluate 18 open-source VLMs (0.3B-32B) based on two key metrics: percentage of PII probing queries refused (Refusal Rate) and the fraction of non-refusal responses flagged for containing PII (Conditional PII Disclosure Rate). Across models, we observe a consistent pattern: refusals increase and PII disclosures decrease (9.10% high to 5.34% low) as subject visibility drops. We identify that models are more likely to disclose PII for high-visibility subjects, alongside substantial model-family heterogeneity and PII-type disparities. Finally, paraphrasing and jailbreak-style prompts expose attack and model-dependent failures, motivating visibility-aware safety evaluation and training interventions.

Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in various domains. While these advancements promise significant productivity gains, they also introduce critical safety risks that remain under-explored. Existing safety evaluations primarily focus on simple, daily assistance tasks, failing to capture the intricate decision-making processes and potential consequences of misaligned behaviors in professional settings. To address this gap, we introduce SafePro, a comprehensive benchmark designed to evaluate the safety alignment of AI agents performing professional activities. SafePro features a dataset of high-complexity tasks across diverse professional domains with safety risks, developed through a rigorous iterative creation and review process. Our evaluation of state-of-the-art AI models reveals significant safety vulnerabilities and uncovers new unsafe behaviors in professional contexts. We further show that these models exhibit both insufficient safety judgment and weak safety alignment when executing complex professional tasks. In addition, we investigate safety mitigation strategies for improving agent safety in these scenarios and observe encouraging improvements. Together, our findings highlight the urgent need for robust safety mechanisms tailored to the next generation of professional AI agents.

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.

Large Language Models (LLMs) rely on safety alignment to produce socially acceptable responses. This is typically achieved through instruction tuning and reinforcement learning from human feedback. However, this alignment is known to be brittle: further fine-tuning, even on benign or lightly contaminated data, can degrade safety and reintroduce harmful behaviors. A growing body of work suggests that alignment may correspond to identifiable geometric directions in weight space, forming subspaces that could, in principle, be isolated or preserved to defend against misalignment. In this work, we conduct a comprehensive empirical study of this geometric perspective. We examine whether safety-relevant behavior is concentrated in specific subspaces, whether it can be separated from general-purpose learning, and whether harmfulness arises from distinguishable patterns in internal representations. Across both parameter and activation space, our findings are consistent: subspaces that amplify safe behaviors also amplify unsafe ones, and prompts with different safety implications activate overlapping representations. We find no evidence of a subspace that selectively governs safety. These results challenge the assumption that alignment is geometrically localized. Rather than residing in distinct directions, safety appears to emerge from entangled, high-impact components of the model's broader learning dynamics. This suggests that subspace-based defenses may face fundamental limitations and underscores the need for alternative strategies to preserve alignment under continued training. We corroborate these findings through multiple experiments on five open-source LLMs. Our code is publicly available at: https://github.com/CERT-Lab/safety-subspaces.

The current safeguard mechanisms for large language models (LLMs) are indeed susceptible to jailbreak attacks, making them inherently fragile. Even the process of fine-tuning on apparently benign data for downstream tasks can jeopardize safety. One potential solution is to conduct safety fine-tuning subsequent to downstream fine-tuning. However, there's a risk of catastrophic forgetting during safety fine-tuning, where LLMs may regain safety measures but lose the task-specific knowledge acquired during downstream fine-tuning. In this paper, we introduce a safety realignment framework through subspace-oriented model fusion (SOMF), aiming to combine the safeguard capabilities of initially aligned model and the current fine-tuned model into a realigned model. Our approach begins by disentangling all task vectors from the weights of each fine-tuned model. We then identify safety-related regions within these vectors by subspace masking techniques. Finally, we explore the fusion of the initial safely aligned LLM with all task vectors based on the identified safety subspace. We validate that our safety realignment framework satisfies the safety requirements of a single fine-tuned model as well as multiple models during their fusion. Our findings confirm that SOMF preserves safety without notably compromising performance on downstream tasks, including instruction following in Chinese, English, and Hindi, as well as problem-solving capabilities in Code and Math.

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 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.

Although large language models (LLMs) achieve effective safety alignment at the time of release, they still face various safety challenges. A key issue is that fine-tuning often compromises the safety alignment of LLMs. To address this issue, we propose a method named IRR (Identify, Remove, and Recalibrate for Safety Realignment) that performs safety realignment for LLMs. The core of IRR is to identify and remove unsafe delta parameters from the fine-tuned models, while recalibrating the retained ones. We evaluate the effectiveness of IRR across various datasets, including both full fine-tuning and LoRA methods. Our results demonstrate that IRR significantly enhances the safety performance of fine-tuned models on safety benchmarks, such as harmful queries and jailbreak attacks, while maintaining their performance on downstream tasks. The source code is available at: https://anonymous.4open.science/r/IRR-BD4F.

Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatically. Existing safety evaluations largely target explicit threats such as misuse and prompt injection, but overlook a subtle yet critical setting where user instructions are entirely benign and harm arises from the task context or execution outcome. We introduce OS-BLIND, a benchmark that evaluates CUAs under unintended attack conditions, comprising 300 human-crafted tasks across 12 categories, 8 applications, and 2 threat clusters: environment-embedded threats and agent-initiated harms. Our evaluation on frontier models and agentic frameworks reveals that most CUAs exceed 90% attack success rate (ASR), and even the safety-aligned Claude 4.5 Sonnet reaches 73.0% ASR. More interestingly, this vulnerability becomes even more severe, with ASR rising from 73.0% to 92.7% when Claude 4.5 Sonnet is deployed in multi-agent systems. Our analysis further shows that existing safety defenses provide limited protection when user instructions are benign. Safety alignment primarily activates within the first few steps and rarely re-engages during subsequent execution. In multi-agent systems, decomposed subtasks obscure the harmful intent from the model, causing safety-aligned models to fail. We will release our OS-BLIND to encourage the broader research community to further investigate and address these safety challenges.

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We systematically investigate and compare the influence of six critical intrinsic model characteristics and three external attack techniques. Our large-scale evaluation is conducted using 32 recent, popular LLMs and LRMs across thirteen distinct model families, spanning a parameter scale from 3B to 235B. The assessment leverages five established safety datasets and probes model vulnerabilities with 56 jailbreak techniques and four CoT attack strategies, resulting in 4.6M API calls. Our key empirical findings are fourfold. First, we identify the LRMs GPT-OSS-20B, Qwen3-Next-80B-A3B-Thinking, and GPT-OSS-120B as the top-three safest models, which substantiates the significant advantage of integrated reasoning and self-reflection mechanisms for robust safety alignment. Second, post-training and knowledge distillation may lead to a systematic degradation of safety alignment. We thus argue that safety must be treated as an explicit constraint or a core optimization objective during these stages, not merely subordinated to the pursuit of general capability. Third, we reveal a pronounced vulnerability: employing a CoT attack via a response prefix can elevate the attack success rate by 3.34x on average and from 0.6% to 96.3% for Seed-OSS-36B-Instruct. This critical finding underscores the safety risks inherent in text-completion interfaces and features that allow user-defined response prefixes in LLM services, highlighting an urgent need for architectural and deployment safeguards. Fourth, roleplay, prompt injection, and gradient-based search for adversarial prompts are the predominant methodologies for eliciting unaligned behaviors in modern models.

A key concern with the concept of "alignment" is the implicit question of "alignment to what?". AI systems are increasingly used across the world, yet safety alignment is often focused on homogeneous monolingual settings. Additionally, preference training and safety measures often overfit to harms common in Western-centric datasets. Here, we explore the viability of different alignment approaches when balancing dual objectives: addressing and optimizing for a non-homogeneous set of languages and cultural preferences while minimizing both global and local harms. We collect the first set of human annotated red-teaming prompts in different languages distinguishing between global and local harm, which serve as a laboratory for understanding the reliability of alignment techniques when faced with preference distributions that are non-stationary across geographies and languages. While this setting is seldom covered by the literature to date, which primarily centers on English harm mitigation, it captures real-world interactions with AI systems around the world. We establish a new precedent for state-of-the-art alignment techniques across 6 languages with minimal degradation in general performance. Our work provides important insights into cross-lingual transfer and novel optimization approaches to safeguard AI systems designed to serve global populations.

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.

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.

Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) enhances adaptability while reducing computational costs. However, fine-tuning can compromise safety alignment, even with benign data, increasing susceptibility to harmful outputs. Existing safety alignment methods struggle to capture complex parameter shifts, leading to suboptimal safety-utility trade-offs. To address this issue, we propose Safe Pruning LoRA (SPLoRA), a novel pruning-based approach that selectively removes LoRA layers that weaken safety alignment, improving safety while preserving performance. At its core, we introduce Empirical-DIEM (E-DIEM), a dimension-insensitive similarity metric that effectively detects safety misalignment in LoRA-adapted models. We conduct extensive experiments on LLMs fine-tuned with mixed of benign and malicious data, and purely benign datasets, evaluating SPLoRA across utility, safety, and reliability metrics. Results demonstrate that SPLoRA outperforms state-of-the-art safety alignment techniques, significantly reducing safety risks while maintaining or improving model performance and reliability. Additionally, SPLoRA reduces inference overhead, making it a scalable and efficient solution for deploying safer and more reliable LLMs. The code is available at https://github.com/AoShuang92/SPLoRA.

Fine-tuning-as-a-Service introduces a critical vulnerability where a few malicious examples mixed into the user's fine-tuning dataset can compromise the safety alignment of Large Language Models (LLMs). While a recognized paradigm frames safe fine-tuning as a multi-objective optimization problem balancing user task performance with safety alignment, we find existing solutions are critically sensitive to the harmful ratio, with defenses degrading sharply as harmful ratio increases. We diagnose that this failure stems from conflicting gradients, where the user-task update directly undermines the safety objective. To resolve this, we propose SafeGrad, a novel method that employs gradient surgery. When a conflict is detected, SafeGrad nullifies the harmful component of the user-task gradient by projecting it onto the orthogonal plane of the alignment gradient, allowing the model to learn the user's task without sacrificing safety. To further enhance robustness and data efficiency, we employ a KL-divergence alignment loss that learns the rich, distributional safety profile of the well-aligned foundation model. Extensive experiments show that SafeGrad provides state-of-the-art defense across various LLMs and datasets, maintaining robust safety even at high harmful ratios without compromising task fidelity.

Fine-tuning large language models (LLMs) for downstream tasks is a widely adopted approach, but it often leads to safety degradation in safety-aligned LLMs. Currently, many solutions address this issue by incorporating additional safety data, which can be impractical in many cases. In this paper, we address the question: How can we improve downstream task performance while preserving safety in LLMs without relying on additional safety data? We propose a simple and effective method that maintains the inherent safety of LLMs while enhancing their downstream task performance: merging the weights of pre- and post-fine-tuned safety-aligned models. Experimental results across various downstream tasks, models, and merging methods demonstrate that this approach effectively mitigates safety degradation while improving downstream task performance, offering a practical solution for adapting safety-aligned LLMs.

Public LLMs such as the Llama 2-Chat have driven huge activity in LLM research. These models underwent alignment training and were considered safe. Recently Qi et al. (2023) reported that even benign fine-tuning (e.g., on seemingly safe datasets) can give rise to unsafe behaviors in the models. The current paper is about methods and best practices to mitigate such loss of alignment. Through extensive experiments on several chat models (Meta's Llama 2-Chat, Mistral AI's Mistral 7B Instruct v0.2, and OpenAI's GPT-3.5 Turbo), this paper uncovers that the prompt templates used during fine-tuning and inference play a crucial role in preserving safety alignment, and proposes the "Pure Tuning, Safe Testing" (PTST) principle -- fine-tune models without a safety prompt, but include it at test time. Fine-tuning experiments on GSM8K, ChatDoctor, and OpenOrca show that PTST significantly reduces the rise of unsafe behaviors, and even almost eliminates them in some cases.

Large language models (LLMs) show inherent brittleness in their safety mechanisms, as evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This study explores this brittleness of safety alignment by leveraging pruning and low-rank modifications. We develop methods to identify critical regions that are vital for safety guardrails, and that are disentangled from utility-relevant regions at both the neuron and rank levels. Surprisingly, the isolated regions we find are sparse, comprising about 3% at the parameter level and 2.5% at the rank level. Removing these regions compromises safety without significantly impacting utility, corroborating the inherent brittleness of the model's safety mechanisms. Moreover, we show that LLMs remain vulnerable to low-cost fine-tuning attacks even when modifications to the safety-critical regions are restricted. These findings underscore the urgent need for more robust safety strategies in LLMs.

As the influence of large language models (LLMs) spans across global communities, their safety challenges in multilingual settings become paramount for alignment research. This paper examines the variations in safety challenges faced by LLMs across different languages and discusses approaches to alleviating such concerns. By comparing how state-of-the-art LLMs respond to the same set of malicious prompts written in higher- vs. lower-resource languages, we observe that (1) LLMs tend to generate unsafe responses much more often when a malicious prompt is written in a lower-resource language, and (2) LLMs tend to generate more irrelevant responses to malicious prompts in lower-resource languages. To understand where the discrepancy can be attributed, we study the effect of instruction tuning with reinforcement learning from human feedback (RLHF) or supervised finetuning (SFT) on the HH-RLHF dataset. Surprisingly, while training with high-resource languages improves model alignment, training in lower-resource languages yields minimal improvement. This suggests that the bottleneck of cross-lingual alignment is rooted in the pretraining stage. Our findings highlight the challenges in cross-lingual LLM safety, and we hope they inform future research in this direction.

Large language models (LLMs) have had a transformative impact on a variety of scientific tasks across disciplines such as biology, chemistry, medicine, and physics. However, ensuring the safety alignment of these models in scientific research remains an underexplored area, with existing benchmarks primarily focus on textual content and overlooking key scientific representations such as molecular, protein, and genomic languages. Moreover, the safety mechanisms of LLMs in scientific tasks are insufficiently studied. To address these limitations, we introduce SciSafeEval, a comprehensive benchmark designed to evaluate the safety alignment of LLMs across a range of scientific tasks. SciSafeEval spans multiple scientific languages - including textual, molecular, protein, and genomic - and covers a wide range of scientific domains. We evaluate LLMs in zero-shot, few-shot and chain-of-thought settings, and introduce a 'jailbreak' enhancement feature that challenges LLMs equipped with safety guardrails, rigorously testing their defenses against malicious intention. Our benchmark surpasses existing safety datasets in both scale and scope, providing a robust platform for assessing the safety and performance of LLMs in scientific contexts. This work aims to facilitate the responsible development and deployment of LLMs, promoting alignment with safety and ethical standards in scientific research.

Large language models (LLMs), despite possessing latent safety understanding from their vast pretraining data, remain vulnerable to generating harmful content and exhibit issues such as over-refusal and utility degradation after safety alignment. Current safety alignment methods often result in superficial refusal shortcuts or rely on intensive supervision for reasoning-based approaches, failing to fully leverage the model's intrinsic safety self-awareness. We propose AlphaAlign, a simple yet effective pure reinforcement learning (RL) framework with verifiable safety reward designed to incentivize this latent safety awareness through proactive safety reasoning.} AlphaAlign employs a dual-reward system: a verifiable safety reward encourages correctly formatted and explicitly justified refusals for harmful queries while penalizing over-refusals, and a normalized helpfulness reward guides high-quality responses to benign inputs. This allows the model to develop proactive safety reasoning capabilities without depending on supervised safety-specific reasoning data. AlphaAlign demonstrates three key advantages: (1) Simplicity and efficiency, requiring only binary prompt safety labels and minimal RL steps for substantial improvements. (2) Breaking the safety-utility trade-off, by enhancing refusal of harmful content and reducing over-refusals, while simultaneously maintaining or even improving general task performance and robustness to unseen jailbreaks. (3) Deep alignment, fostering proactive safety reasoning that generates explicit safety rationales rather than relying on shallow refusal patterns.

As advancements in large language models (LLMs) continue and the demand for personalized models increases, parameter-efficient fine-tuning (PEFT) methods (e.g., LoRA) will become essential due to their efficiency in reducing computation costs. However, recent studies have raised alarming concerns that LoRA fine-tuning could potentially compromise the safety alignment in LLMs, posing significant risks for the model owner. In this paper, we first investigate the underlying mechanism by analyzing the changes in safety alignment related features before and after fine-tuning. Then, we propose a fixed safety module calculated by safety data and a task-specific initialization for trainable parameters in low-rank adaptations, termed Safety-alignment preserved Low-Rank Adaptation (SaLoRA). Unlike previous LoRA methods and their variants, SaLoRA enables targeted modifications to LLMs without disrupting their original alignments. Our experiments show that SaLoRA outperforms various adapters-based approaches across various evaluation metrics in different fine-tuning tasks.

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We argue that this stems from the shallow nature of existing alignment methods, which focus on surface-level refusal behaviors without sufficiently altering internal representations. Consequently, small shifts in hidden activations can re-trigger harmful behaviors embedded in the latent space. To explore the robustness of safety alignment to latent perturbations, we introduce a probing method that measures the Negative Log-Likelihood of the original response generated by the model. This probe quantifies local sensitivity in the latent space, serving as a diagnostic tool for identifying vulnerable directions. Based on this signal, we construct effective jailbreak trajectories, giving rise to the Activation Steering Attack (ASA). More importantly, these insights offer a principled foundation for improving alignment robustness. To this end, we introduce Layer-wise Adversarial Patch Training~(LAPT), a fine-tuning strategy that inject controlled perturbations into hidden representations during training. Experimental results highlight that LAPT strengthen alignment robustness without compromising general capabilities. Our findings reveal fundamental flaws in current alignment paradigms and call for representation-level training strategies that move beyond surface-level behavior supervision. Codes and results are available at https://github.com/Carol-gutianle/LatentSafety.

Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as jailbreaking but also to inadvertently generating harmful content for benign users. While internal safety alignment via Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) is a primary mitigation strategy, current methods often face a safety-utility trade-off: they either refuse benign queries out of excessive caution or overlook latent risks in cross-modal interactions. To resolve this, we introduce Pragma-VL, an end-to-end alignment algorithm that enables MLLMs to pragmatically arbitrate between safety and helpfulness. First, we enhance visual risk perception with a novel cold-start SFT stage. This is achieved by applying risk-aware clustering to the visual encoder and using an interleaved dataset of risk descriptions and high-quality data. Second, we introduce a theoretically-guaranteed reward model that leverages synergistic learning. We train it with a novel data augmentation method that assigns dynamic weights based on the queries, enabling contextual arbitration between safety and helpfulness. Extensive experiments show that Pragma-VL effectively balances safety and helpfulness, outperforming baselines by 5% to 20% on most multimodal safety benchmarks while preserving its general capabilities in areas such as mathematics and knowledge reasoning.

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.

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

Safety alignment is essential for the responsible deployment of large language models (LLMs). Yet, existing approaches often rely on heavyweight fine-tuning that is costly to update, audit, and maintain across model families. Full fine-tuning incurs substantial computational and storage overhead, while parameter-efficient methods such as LoRA trade efficiency for inconsistent safety gains and sensitivity to design choices. Safety intervention mechanisms such as circuit breakers reduce unsafe outputs without modifying model weights, but do not directly shape or preserve the internal representations that govern safety behavior. These limitations hinder rapid and reliable safety updates, particularly in settings where models evolve frequently or must adapt to new policies and domains. We present NeST, a lightweight, structure-aware safety alignment framework that strengthens refusal behavior by selectively adapting a small subset of safety-relevant neurons while freezing the remainder of the model. NeST aligns parameter updates with the internal organization of safety behavior by clustering functionally coherent safety neurons and enforcing shared updates within each cluster, enabling targeted and stable safety adaptation without broad model modification or inference-time overhead. We benchmark NeST against three dominant baselines: full fine-tuning, LoRA-based fine-tuning, and circuit breakers across 10 open-weight LLMs spanning multiple model families and sizes. Across all evaluated models, NeST reduces the attack success rate from an average of 44.5% to 4.36%, corresponding to a 90.2% reduction in unsafe generations, while requiring only 0.44 million trainable parameters on average. This amounts to a 17,310x decrease in updated parameters compared to full fine-tuning and a 9.25x reduction relative to LoRA, while consistently achieving stronger safety performance for alignment.

Language Model Models (LLMs) have improved dramatically in the past few years, increasing their adoption and the scope of their capabilities over time. A significant amount of work is dedicated to ``model alignment'', i.e., preventing LLMs to generate unsafe responses when deployed into customer-facing applications. One popular method to evaluate safety risks is red-teaming, where agents attempt to bypass alignment by crafting elaborate prompts that trigger unsafe responses from a model. Standard human-driven red-teaming is costly, time-consuming and rarely covers all the recent features (e.g., multi-lingual, multi-modal aspects), while proposed automation methods only cover a small subset of LLMs capabilities (i.e., English or single-turn). We present Multi-lingual Multi-turn Automated Red Teaming (MM-ART), a method to fully automate conversational, multi-lingual red-teaming operations and quickly identify prompts leading to unsafe responses. Through extensive experiments on different languages, we show the studied LLMs are on average 71\% more vulnerable after a 5-turn conversation in English than after the initial turn. For conversations in non-English languages, models display up to 195\% more safety vulnerabilities than the standard single-turn English approach, confirming the need for automated red-teaming methods matching LLMs capabilities.

As large reasoning models (LRMs) grow more capable, chain-of-thought (CoT) reasoning introduces new safety challenges. Existing SFT-based safety alignment studies dominantly focused on filtering prompts with safe, high-quality responses, while overlooking hard prompts that always elicit harmful outputs. To fill this gap, we introduce UnsafeChain, a safety alignment dataset constructed from hard prompts with diverse sources, where unsafe completions are identified and explicitly corrected into safe responses. By exposing models to unsafe behaviors and guiding their correction, UnsafeChain enhances safety while preserving general reasoning ability. We fine-tune three LRMs on UnsafeChain and compare them against recent SafeChain and STAR-1 across six out-of-distribution and five in-distribution benchmarks. UnsafeChain consistently outperforms prior datasets, with even a 1K subset matching or surpassing baseline performance, demonstrating the effectiveness and generalizability of correction-based supervision. We release our dataset and code at https://github.com/mbzuai-nlp/UnsafeChain

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.

Safety alignment in language models operates through two mechanistically distinct systems: refusal neurons that gate whether harmful knowledge is expressed, and concept neurons that encode the harmful knowledge itself. By targeting a single neuron in each system, we demonstrate both directions of failure -- bypassing safety on explicit harmful requests via suppression, and inducing harmful content from innocent prompts via amplification -- across seven models spanning two families and 1.7B to 70B parameters, without any training or prompt engineering. Our findings suggest that safety alignment is not robustly distributed across model weights but is mediated by individual neurons that are each causally sufficient to gate refusal behavior -- suppressing any one of the identified refusal neurons bypasses safety alignment across diverse harmful requests.

Despite the rapid advancements of Large Language Models (LLMs), safety risks remain a critical challenge for low-resource languages. Existing safety datasets are predominantly English centric, limiting progress in multilingual safety alignment. As a result, low resource expert models, finetuned on their respective instruction datasets, tend to exhibit higher unsafety rates compared to their high resource counterparts. In this work, we propose a safety aware layer swapping method that transfers safety alignment from an English safety expert to low resource language experts without additional training. To further enhance transfer ability, our method adaptively selects or blends modules based on their degree of specialization. Our approach preserves performance on general language understanding tasks while enhancing safety in the target languages. Experimental results show that the proposed method achieves comparable performance to the language expert on general benchmarks such as MMMLU, BELEBELE, and MGSM, while producing more aligned and less harmful responses on the MultiJail safety benchmark.

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.

The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthiness, adversaries can exploit these techniques to undermine safety for malicious purposes, resulting in misalignment. Misaligned LLMs may be published on open platforms to magnify harm. To address this, additional safety alignment, referred to as realignment, is necessary before deploying untrusted third-party LLMs. This study explores the efficacy of fine-tuning methods in terms of misalignment, realignment, and the effects of their interplay. By evaluating four Supervised Fine-Tuning (SFT) and two Preference Fine-Tuning (PFT) methods across four popular safety-aligned LLMs, we reveal a mechanism asymmetry between attack and defense. While Odds Ratio Preference Optimization (ORPO) is most effective for misalignment, Direct Preference Optimization (DPO) excels in realignment, albeit at the expense of model utility. Additionally, we identify model-specific resistance, residual effects of multi-round adversarial dynamics, and other noteworthy findings. These findings highlight the need for robust safeguards and customized safety alignment strategies to mitigate potential risks in the deployment of LLMs. Our code is available at https://github.com/zhangrui4041/The-Art-of-Mis-alignment.

The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. This becomes particularly evident when LLMs inadvertently generate harmful or toxic content, either unintentionally or because of intentional inducement. Existing alignment methods usually direct LLMs toward the favorable outcomes by utilizing human-annotated, flawless instruction-response pairs. Conversely, this study proposes a novel alignment technique based on mistake analysis, which deliberately exposes LLMs to erroneous content to learn the reasons for mistakes and how to avoid them. In this case, mistakes are repurposed into valuable data for alignment, effectively helping to avoid the production of erroneous responses. Without external models or human annotations, our method leverages a model's intrinsic ability to discern undesirable mistakes and improves the safety of its generated responses. Experimental results reveal that our method outperforms existing alignment approaches in enhancing model safety while maintaining the overall utility.

Many machine learning models are fine-tuned from large language models (LLMs) to achieve high performance in specialized domains like code generation, biomedical analysis, and mathematical problem solving. However, this fine-tuning process often introduces a critical vulnerability: the systematic degradation of safety alignment, undermining ethical guidelines and increasing the risk of harmful outputs. Addressing this challenge, we introduce EnchTable, a novel framework designed to transfer and maintain safety alignment in downstream LLMs without requiring extensive retraining. EnchTable leverages a Neural Tangent Kernel (NTK)-based safety vector distillation method to decouple safety constraints from task-specific reasoning, ensuring compatibility across diverse model architectures and sizes. Additionally, our interference-aware merging technique effectively balances safety and utility, minimizing performance compromises across various task domains. We implemented a fully functional prototype of EnchTable on three different task domains and three distinct LLM architectures, and evaluated its performance through extensive experiments on eleven diverse datasets, assessing both utility and model safety. Our evaluations include LLMs from different vendors, demonstrating EnchTable's generalization capability. Furthermore, EnchTable exhibits robust resistance to static and dynamic jailbreaking attacks, outperforming vendor-released safety models in mitigating adversarial prompts. Comparative analyses with six parameter modification methods and two inference-time alignment baselines reveal that EnchTable achieves a significantly lower unsafe rate, higher utility score, and universal applicability across different task domains. Additionally, we validate EnchTable can be seamlessly integrated into various deployment pipelines without significant overhead.

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.

Critical Error Detection (CED) in machine translation aims to determine whether a translation is safe to use or contains unacceptable deviations in meaning. While the WMT21 English-German CED dataset provided the first benchmark, it is limited in scale, label balance, domain coverage, and temporal freshness. We present SynCED-EnDe, a new resource consisting of 1,000 gold-labeled and 8,000 silver-labeled sentence pairs, balanced 50/50 between error and non-error cases. SynCED-EnDe draws from diverse 2024-2025 sources (StackExchange, GOV.UK) and introduces explicit error subclasses, structured trigger flags, and fine-grained auxiliary judgments (obviousness, severity, localization complexity, contextual dependency, adequacy deviation). These enrichments enable systematic analyses of error risk and intricacy beyond binary detection. The dataset is permanently hosted on GitHub and Hugging Face, accompanied by documentation, annotation guidelines, and baseline scripts. Benchmark experiments with XLM-R and related encoders show substantial performance gains over WMT21 due to balanced labels and refined annotations. We envision SynCED-EnDe as a community resource to advance safe deployment of MT in information retrieval and conversational assistants, particularly in emerging contexts such as wearable AI devices.

Text-to-image (T2I) models are widespread, but their limited safety guardrails expose end users to harmful content and potentially allow for model misuse. Current safety measures are typically limited to text-based filtering or concept removal strategies, able to remove just a few concepts from the model's generative capabilities. In this work, we introduce AlignGuard, a method for safety alignment of T2I models. We enable the application of Direct Preference Optimization (DPO) for safety purposes in T2I models by synthetically generating a dataset of harmful and safe image-text pairs, which we call CoProV2. Using a custom DPO strategy and this dataset, we train safety experts, in the form of low-rank adaptation (LoRA) matrices, able to guide the generation process away from specific safety-related concepts. Then, we merge the experts into a single LoRA using a novel merging strategy for optimal scaling performance. This expert-based approach enables scalability, allowing us to remove 7x more harmful concepts from T2I models compared to baselines. AlignGuard consistently outperforms the state-of-the-art on many benchmarks and establishes new practices for safety alignment in T2I networks. Code and data will be shared at https://safetydpo.github.io/.

Safety and efficiency are paramount yet often conflicting requirements for deploying Large Language Models (LLMs). While LLMs are trained to follow human alignment for safety, Post-Training Quantization (PTQ) is applied afterward to ensure efficiency. Here we identify a fundamental flaw in the conventional PTQ paradigm: quantization can turn into a safety vulnerability if it only aims to achieve low perplexity. To address this, we propose Alignment-Aware Quantization (AAQ), a novel approach that integrates an Alignment-Preserving Contrastive (APC) loss into the PTQ pipeline. Our method explicitly preserves alignment by encouraging the quantized model to mimic its safe, instruction-tuned model while diverging from the unaligned, pre-trained counterpart. AAQ achieves robust safety alignment without specialized safety-focused datasets, using only standard calibration data. We show that AAQ is compatible with standard PTQ techniques and enables robust 4-bit (W4A4) quantization across diverse model families. Our work resolves the critical trade-off between efficiency and safety, paving the way toward LLMs that are both efficient and trustworthy. Anonymized code is available in the supplementary material.

Safety alignment in Large Language Models (LLMs) often involves mediating internal representations to refuse harmful requests. Recent research has demonstrated that these safety mechanisms can be bypassed by ablating or removing specific representational directions within the model. In this paper, we propose the opposite approach: Rank-One Safety Injection (ROSI), a white-box method that amplifies a model's safety alignment by permanently steering its activations toward the refusal-mediating subspace. ROSI operates as a simple, fine-tuning-free rank-one weight modification applied to all residual stream write matrices. The required safety direction can be computed from a small set of harmful and harmless instruction pairs. We show that ROSI consistently increases safety refusal rates - as evaluated by Llama Guard 3 - while preserving the utility of the model on standard benchmarks such as MMLU, HellaSwag, and Arc. Furthermore, we show that ROSI can also re-align 'uncensored' models by amplifying their own latent safety directions, demonstrating its utility as an effective last-mile safety procedure. Our results suggest that targeted, interpretable weight steering is a cheap and potent mechanism to improve LLM safety, complementing more resource-intensive fine-tuning paradigms.

As large language models (LLMs) evolve from conversational assistants into autonomous agents, evaluating the safety of their actions becomes critical. Prior safety benchmarks have primarily focused on preventing generation of harmful content, such as toxic text. However, they overlook the challenge of agents taking harmful actions when the most effective path to an operational goal conflicts with human safety. To address this gap, we introduce ManagerBench, a benchmark that evaluates LLM decision-making in realistic, human-validated managerial scenarios. Each scenario forces a choice between a pragmatic but harmful action that achieves an operational goal, and a safe action that leads to worse operational performance. A parallel control set, where potential harm is directed only at inanimate objects, measures a model's pragmatism and identifies its tendency to be overly safe. Our findings indicate that the frontier LLMs perform poorly when navigating this safety-pragmatism trade-off. Many consistently choose harmful options to advance their operational goals, while others avoid harm only to become overly safe and ineffective. Critically, we find this misalignment does not stem from an inability to perceive harm, as models' harm assessments align with human judgments, but from flawed prioritization. ManagerBench is a challenging benchmark for a core component of agentic behavior: making safe choices when operational goals and alignment values incentivize conflicting actions. Benchmark & code available at https://github.com/technion-cs-nlp/ManagerBench.

Larger language models (LLMs) have taken the world by storm with their massive multi-tasking capabilities simply by optimizing over a next-word prediction objective. With the emergence of their properties and encoded knowledge, the risk of LLMs producing harmful outputs increases, making them unfit for scalable deployment for the public. In this work, we propose a new safety evaluation benchmark RED-EVAL that carries out red-teaming. We show that even widely deployed models are susceptible to the Chain of Utterances-based (CoU) prompting, jailbreaking closed source LLM-based systems such as GPT-4 and ChatGPT to unethically respond to more than 65% and 73% of harmful queries. We also demonstrate the consistency of the RED-EVAL across 8 open-source LLMs in generating harmful responses in more than 86% of the red-teaming attempts. Next, we propose RED-INSTRUCT--An approach for the safety alignment of LLMs. It constitutes two phases: 1) HARMFULQA data collection: Leveraging CoU prompting, we collect a dataset that consists of 1.9K harmful questions covering a wide range of topics, 9.5K safe and 7.3K harmful conversations from ChatGPT; 2) SAFE-ALIGN: We demonstrate how the conversational dataset can be used for the safety alignment of LLMs by minimizing the negative log-likelihood over helpful responses and penalizing over harmful responses by gradient accent over sample loss. Our model STARLING, a fine-tuned Vicuna-7B, is observed to be more safely aligned when evaluated on RED-EVAL and HHH benchmarks while preserving the utility of the baseline models (TruthfulQA, MMLU, and BBH).

In recent years, safety risks associated with large language models have become increasingly prominent, highlighting the urgent need to mitigate the generation of toxic and harmful content. The mainstream paradigm for LLM safety alignment typically adopts a collaborative framework involving three roles: an attacker for adversarial prompt generation, a defender for safety defense, and an evaluator for response assessment. In this paper, we propose a closed-loop reinforcement learning framework called TriPlay-RL that enables iterative and co-improving collaboration among three roles with near-zero manual annotation. Experimental results show that the attacker preserves high output diversity while achieving a 20%-50% improvement in adversarial effectiveness; the defender attains 10%-30% gains in safety performance without degrading general reasoning capability; and the evaluator continuously refines its fine-grained judgment ability through iterations, accurately distinguishing unsafe responses, simple refusals, and useful guidance. Overall, our framework establishes an efficient and scalable paradigm for LLM safety alignment, enabling continuous co-evolution within a unified learning loop.

Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical safety challenges. Existing alignment methods often struggle to cover diverse safety scenarios and remain vulnerable to adversarial attacks. In this work, we propose Ex-Ante Reasoning Preference Optimization (ERPO), a novel safety alignment framework that equips LLMs with explicit preemptive reasoning through Chain-of-Thought and provides clear evidence for safety judgments by embedding predefined safety rules. Specifically, our approach consists of three stages: first, equipping the model with Ex-Ante reasoning through supervised fine-tuning (SFT) using a constructed reasoning module; second, enhancing safety, usefulness, and efficiency via Direct Preference Optimization (DPO); and third, mitigating inference latency with a length-controlled iterative preference optimization strategy. Experiments on multiple open-source LLMs demonstrate that ERPO significantly enhances safety performance while maintaining response efficiency.

The growing awareness of safety concerns in large language models (LLMs) has sparked considerable interest in the evaluation of safety within current research endeavors. This study investigates an interesting issue pertaining to the evaluation of LLMs, namely the substantial discrepancy in performance between multiple-choice questions and open-ended questions. Inspired by research on jailbreak attack patterns, we argue this is caused by mismatched generalization. That is, the LLM does not have a comprehensive understanding of the complex concept of safety. Instead, it only remembers what to answer for open-ended safety questions, which makes it unable to solve other forms of safety tests. We refer to this phenomenon as fake alignment and construct a comparative benchmark to empirically verify its existence in LLMs. Such fake alignment renders previous evaluation protocols unreliable. To address this, we introduce the Fake alIgNment Evaluation (FINE) framework and two novel metrics--Consistency Score (CS) and Consistent Safety Score (CSS), which jointly assess two complementary forms of evaluation to quantify fake alignment and obtain corrected performance estimates. Applying FINE to 14 widely-used LLMs reveals several models with purported safety are poorly aligned in practice. Our work highlights potential limitations in prevailing alignment methodologies.

Large reasoning models (LRMs) extend large language models by generating explicit chain-of-thought (CoT) reasoning, significantly improving mathematical and logical problem solving. However, this explicit reasoning process also introduces new safety risks, as unsafe behaviors often emerge within intermediate reasoning trajectories, even when final answers appear harmless. Existing safety alignment approaches primarily rely on supervised fine-tuning (SFT) over safety-oriented long CoT datasets. While intuitive, we find that SFT produces inconsistent safety improvements, degrades reasoning ability, and generalizes poorly across model families. These limitations suggest that purely supervised approaches are insufficient for robust safety alignment in LRMs. To address this, we investigate reinforcement learning (RL) as a complementary optimization framework for LRM safety training. Unlike SFT, RL directly optimizes model policies with reward feedback, enabling more adaptive and stable alignment. Extensive experiments across multiple model families and benchmarks show that RL achieves stronger and more consistent safety gains while maintaining reasoning competence. Further analysis of reflection dynamics and token-level entropy reveals that RL suppresses unsafe exploratory reasoning while preserving reflective depth, leading to safer and more reliable reasoning processes.

AI alignment aims to make AI systems behave in line with human intentions and values. As AI systems grow more capable, so do risks from misalignment. To provide a comprehensive and up-to-date overview of the alignment field, in this survey, we delve into the core concepts, methodology, and practice of alignment. First, we identify four principles as the key objectives of AI alignment: Robustness, Interpretability, Controllability, and Ethicality (RICE). Guided by these four principles, we outline the landscape of current alignment research and decompose them into two key components: forward alignment and backward alignment. The former aims to make AI systems aligned via alignment training, while the latter aims to gain evidence about the systems' alignment and govern them appropriately to avoid exacerbating misalignment risks. On forward alignment, we discuss techniques for learning from feedback and learning under distribution shift. On backward alignment, we discuss assurance techniques and governance practices. We also release and continually update the website (www.alignmentsurvey.com) which features tutorials, collections of papers, blog posts, and other resources.

As Large Language Models (LLMs) become increasingly integrated into real-world applications, ensuring their outputs align with human values and safety standards has become critical. The field has developed diverse alignment approaches including traditional fine-tuning methods (RLHF, instruction tuning), post-hoc correction systems, and inference-time interventions, each with distinct advantages and limitations. However, the lack of unified evaluation frameworks makes it difficult to systematically compare these paradigms and guide deployment decisions. This paper introduces a multi-dimensional evaluation of alignment techniques for LLMs, a comprehensive evaluation framework that provides a systematic comparison across all major alignment paradigms. Our framework assesses methods along four key dimensions: alignment detection, alignment quality, computational efficiency, and robustness. Through experiments across diverse base models and alignment strategies, we demonstrate the utility of our framework in identifying strengths and limitations of current state-of-the-art models, providing valuable insights for future research directions.

From the perspective of content safety issues, alignment has shown to limit large language models' (LLMs) harmful content generation. This intentional method of reinforcing models to not respond to certain user inputs seem to be present in many modern open-source instruction tuning datasets such as OpenAssistant or Guanaco. We introduce a novel insight to an instruction-tuned model's performance affected by the presence of alignment in supervised fine-tuning dataset. To be specific, we noticed that alignment acts as if it is poisoning the instruction dataset. Experimentally, we demonstrate that aligned answers significantly worsen the performance of the resulting fine-tuned model's on various reasoning benchmarks such as Big Bench (BBH), Massive Multitask Language Understanding (MMLU), Human Eval, and Discrete Reasoning Over Paragraphs (DROP), performing worse than the counterpart tuned without alignment by 4-33%.

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-scale language models increasingly impact safety-critical domains, ensuring their reliable adherence to well-defined principles remains a fundamental challenge. We introduce Deliberative Alignment, a new paradigm that directly teaches the model safety specifications and trains it to explicitly recall and accurately reason over the specifications before answering. We used this approach to align OpenAI's o-series models, and achieved highly precise adherence to OpenAI's safety policies, without requiring human-written chain-of-thoughts or answers. Deliberative Alignment pushes the Pareto frontier by simultaneously increasing robustness to jailbreaks while decreasing overrefusal rates, and also improves out-of-distribution generalization. We demonstrate that reasoning over explicitly specified policies enables more scalable, trustworthy, and interpretable alignment.

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.

Large Vision-Language Models (LVLMs) have made significant strides in multimodal comprehension, thanks to extensive pre-training and fine-tuning on large-scale visual datasets. However, despite their robust textual safety mechanisms, they remain vulnerable to harmful visual inputs. Existing safeguards-typically relying on pre-filtering or fine-tuning-incur high costs and diminish overall utility. To address this critical vulnerability, we introduce SafeCLIP, a lightweight method that leverages LVLMs inherent multimodal alignment for zero-shot toxic image detection. By projecting CLIPs discarded CLS token into its text space and matching it with toxic descriptors, SafeCLIP detects harmful content without any architectural changes-adding minimal latency and enabling dynamic safety corrections during inference and fine-tuning.Experiments show that SafeCLIP achieves a 66.9% defense success rate with only 3.2% false positive rate and 7.2% overhead. In contrast, state-of-the-art methods achieve 52.9% success but have a 10.7% false positive rate and 210% overhead. Our work demonstrates that leveraging inherent multimodal alignment can yield efficient, low-cost LVLM safety. Code is available at anonymous.4open.science/r/safeclip-2C01.

Multimodal large language models (MLLMs) are critical for developing general-purpose AI assistants, yet they face growing safety risks. How can we ensure that MLLMs are safely aligned to prevent undesired behaviors such as discrimination, misinformation, or violations of ethical standards? In a further step, we need to explore how to fine-tune MLLMs to enhance reasoning performance while ensuring they satisfy safety constraints. Fundamentally, this can be formulated as a min-max optimization problem. In this study, we propose Safe RLHF-V, the first multimodal safety alignment framework that jointly optimizes helpfulness and safety using separate multimodal reward and cost models within a Lagrangian-based constrained optimization framework. Given that there is a lack of preference datasets that separate helpfulness and safety in multimodal scenarios, we introduce BeaverTails-V, the first open-source dataset with dual preference annotations for helpfulness and safety, along with multi-level safety labels (minor, moderate, severe). Additionally, we design a Multi-level Guardrail System to proactively defend against unsafe queries and adversarial attacks. By applying the Beaver-Guard-V moderation for 5 rounds of filtering and re-generation on the precursor model, the overall safety of the upstream model is significantly improved by an average of 40.9%. Experimental results demonstrate that fine-tuning different MLLMs with Safe RLHF can effectively enhance model helpfulness while ensuring improved safety. Specifically, Safe RLHF-V improves model safety by 34.2% and helpfulness by 34.3%. All of datasets, models, and code can be found at https://github.com/SafeRLHF-V to support the safety development of MLLMs and reduce potential societal risks.

Robust alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based -- training a reward model on preference pairs and optimizing with reinforcement learning (RL) -- or reward-free -- directly fine-tuning on ranked outputs. Recent research shows that well-tuned reward-based pipelines remain the most robust, and single-response demonstrations can outperform pairwise preference data. However, two key challenges remain: (i) imbalanced safety datasets that over-represent common hazards while neglecting long-tail threats; and (ii) static reward models that ignore task difficulty, limiting optimization efficiency and attainable gains. To address these limitations, we propose DR-IRL, which dynamically adjusts rewards through inverse reinforcement learning. We first construct a balanced safety dataset of seven harmful categories using Chain-of-Draft (CoD) template prompts, which reduce token usage and generation time compared to Chain-of-Thought (CoT). We then train category-specific reward models on this dataset via IRL. Finally, to align the LLM, we introduce GRPO-S (Group Relative Policy Optimization--Scaling), a variant of GRPO that scales the reward during optimization to task difficulty -- data-level hardness measured by CLIP similarity and model-level responsiveness measured by reward gaps. Extensive experiments on multiple benchmarks and LLMs demonstrate that DR-IRL outperforms all baselines in safety alignment while maintaining usefulness.

Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that generalizes broadly. Whether this brittleness reflects a fundamental lack of coherent internal organization for harmfulness remains unclear. Here we use targeted weight pruning as a causal intervention to probe the internal organization of harmfulness in LLMs. We find that harmful content generation depends on a compact set of weights that are general across harm types and distinct from benign capabilities. Aligned models exhibit a greater compression of harm generation weights than unaligned counterparts, indicating that alignment reshapes harmful representations internally--despite the brittleness of safety guardrails at the surface level. This compression explains emergent misalignment: if weights of harmful capabilities are compressed, fine-tuning that engages these weights in one domain can trigger broad misalignment. Consistent with this, pruning harm generation weights in a narrow domain substantially reduces emergent misalignment. Notably, LLMs harmful generation capability is dissociated from how they recognize and explain such content. Together, these results reveal a coherent internal structure for harmfulness in LLMs that may serve as a foundation for more principled approaches to safety.

Safety concerns of Multimodal large language models (MLLMs) have gradually become an important problem in various applications. Surprisingly, previous works indicate a counter-intuitive phenomenon that using textual unlearning to align MLLMs achieves comparable safety performances with MLLMs trained with image-text pairs. To explain such a counter-intuitive phenomenon, we discover a visual safety information leakage (VSIL) problem in existing multimodal safety benchmarks, i.e., the potentially risky and sensitive content in the image has been revealed in the textual query. In this way, MLLMs can easily refuse these sensitive text-image queries according to textual queries. However, image-text pairs without VSIL are common in real-world scenarios and are overlooked by existing multimodal safety benchmarks. To this end, we construct multimodal visual leakless safety benchmark (VLSBench) preventing visual safety leakage from image to textual query with 2.4k image-text pairs. Experimental results indicate that VLSBench poses a significant challenge to both open-source and close-source MLLMs, including LLaVA, Qwen2-VL, Llama3.2-Vision, and GPT-4o. This study demonstrates that textual alignment is enough for multimodal safety scenarios with VSIL, while multimodal alignment is a more promising solution for multimodal safety scenarios without VSIL. Please see our code and data at: http://hxhcreate.github.io/VLSBench

To ensure safe usage, Large Language Models (LLMs) typically undergo alignment with human-defined values. However, this alignment often relies on primarily English data and is biased towards Western-centric values, limiting its effectiveness in low-resource language settings. In this paper, we describe our approach for aligning SEA-Lion-v2.1-Instruct (a Llama3-8B variant) to minimize toxicity in Singlish, an English creole specific to Singapore. We find that supervised fine-tuning and Kahneman-Tversky Optimization (KTO) on paired and unpaired preferences is more sample efficient and yields significantly better results than Direct Preference Optimization (DPO). Our analysis reveals that DPO implicitly enforces a weaker safety objective than KTO, and that SFT complements KTO by improving training stability. Finally, we introduce a simple but novel modification to KTO, KTO-S, which improves training stability through better gradient exploitation. Overall, we present a general approach for safety alignment conducive to low-resource English languages, successfully reducing toxicity by 99\% on our Singlish benchmark, with gains generalizing to the broader TOXIGEN dataset while maintaining strong performance across standard LLM benchmarks.

Large Language Models (LLMs) excel in various natural language processing tasks but remain vulnerable to generating harmful content or being exploited for malicious purposes. Although safety alignment datasets have been introduced to mitigate such risks through supervised fine-tuning (SFT), these datasets often lack comprehensive risk coverage. Most existing datasets focus primarily on lexical diversity while neglecting other critical dimensions. To address this limitation, we propose a novel analysis framework to systematically measure the risk coverage of alignment datasets across three essential dimensions: Lexical Diversity, Malicious Intent, and Jailbreak Tactics. We further introduce TRIDENT, an automated pipeline that leverages persona-based, zero-shot LLM generation to produce diverse and comprehensive instructions spanning these dimensions. Each harmful instruction is paired with an ethically aligned response, resulting in two datasets: TRIDENT-Core, comprising 26,311 examples, and TRIDENT-Edge, with 18,773 examples. Fine-tuning Llama 3.1-8B on TRIDENT-Edge demonstrates substantial improvements, achieving an average 14.29% reduction in Harm Score, and a 20% decrease in Attack Success Rate compared to the best-performing baseline model fine-tuned on the WildBreak dataset.

As Video Large Multimodal Models (VLMMs) rapidly advance, their inherent complexity introduces significant safety challenges, particularly the issue of mismatched generalization where static safety alignments fail to transfer to dynamic video contexts. We introduce SafeVid, a framework designed to instill video-specific safety principles in VLMMs. SafeVid uniquely transfers robust textual safety alignment capabilities to the video domain by employing detailed textual video descriptions as an interpretive bridge, facilitating LLM-based rule-driven safety reasoning. This is achieved through a closed-loop system comprising: 1) generation of SafeVid-350K, a novel 350,000-pair video-specific safety preference dataset; 2) targeted alignment of VLMMs using Direct Preference Optimization (DPO); and 3) comprehensive evaluation via our new SafeVidBench benchmark. Alignment with SafeVid-350K significantly enhances VLMM safety, with models like LLaVA-NeXT-Video demonstrating substantial improvements (e.g., up to 42.39%) on SafeVidBench. SafeVid provides critical resources and a structured approach, demonstrating that leveraging textual descriptions as a conduit for safety reasoning markedly improves the safety alignment of VLMMs. We have made SafeVid-350K dataset (https://huggingface.co/datasets/yxwang/SafeVid-350K) publicly available.

Fine-tuning large language models (LLMs) for telecom tasks and datasets is a common practice to adapt general-purpose models to the telecom domain. However, little attention has been paid to how this process may compromise model safety. Recent research has shown that even benign fine-tuning can degrade the safety alignment of LLMs, causing them to respond to harmful or unethical user queries. In this paper, we investigate this issue for telecom-tuned LLMs using three representative datasets featured by the GenAINet initiative. We show that safety degradation persists even for structured and seemingly harmless datasets such as 3GPP standards and tabular records, indicating that telecom-specific data is not immune to safety erosion during fine-tuning. We further extend our analysis to publicly available Telecom LLMs trained via continual pre-training, revealing that safety alignment is often severely lacking, primarily due to the omission of safety-focused instruction tuning. To address these issues in both fine-tuned and pre-trained models, we conduct extensive experiments and evaluate three safety realignment defenses (SafeInstruct, SafeLoRA, and SafeMERGE) using established red-teaming benchmarks. The results show that, across all settings, the proposed defenses can effectively restore safety after harmful degradation without compromising downstream task performance, leading to Safe teleCOMMunication (SafeCOMM) models. In a nutshell, our work serves as a diagnostic study and practical guide for safety realignment in telecom-tuned LLMs, and emphasizes the importance of safety-aware instruction and fine-tuning for real-world deployments of Telecom LLMs.

Safety lies at the core of developing and deploying large language models (LLMs). However, previous safety benchmarks only concern the safety in one language, e.g. the majority language in the pretraining data such as English. In this work, we build the first multilingual safety benchmark for LLMs, XSafety, in response to the global deployment of LLMs in practice. XSafety covers 14 kinds of commonly used safety issues across 10 languages that span several language families. We utilize XSafety to empirically study the multilingual safety for 4 widely-used LLMs, including both close-API and open-source models. Experimental results show that all LLMs produce significantly more unsafe responses for non-English queries than English ones, indicating the necessity of developing safety alignment for non-English languages. In addition, we propose several simple and effective prompting methods to improve the multilingual safety of ChatGPT by evoking safety knowledge and improving cross-lingual generalization of safety alignment. Our prompting method can significantly reduce the ratio of unsafe responses from 19.1% to 9.7% for non-English queries. We release our data at https://github.com/Jarviswang94/Multilingual_safety_benchmark.

Safety alignment incurs safety tax that perturbs a large reasoning model's (LRM) general reasoning ability. Existing datasets used for safety alignment for an LRM are usually constructed by distilling safety reasoning traces and answers from an external LRM or human labeler. However, such reasoning traces and answers exhibit a distributional gap with the target LRM that needs alignment, and we conjecture such distributional gap is the culprit leading to significant degradation of reasoning ability of the target LRM. Driven by this hypothesis, we propose a safety alignment dataset construction method, dubbed DGR. DGR transforms and refines an existing out-of-distributional safety reasoning dataset to be aligned with the target's LLM inner distribution. Experimental results demonstrate that i) DGR effectively mitigates the safety tax while maintaining safety performance across all baselines, i.e., achieving +30.2\% on DirectRefusal and +21.2\% on R1-ACT improvement in average reasoning accuracy compared to Vanilla SFT; ii) the degree of reasoning degradation correlates with the extent of distribution shift, suggesting that bridging this gap is central to preserving capabilities. Furthermore, we find that safety alignment in LRMs may primarily function as a mechanism to activate latent knowledge, as a mere 10 samples are sufficient for activating effective refusal behaviors. These findings not only emphasize the importance of distributional consistency but also provide insights into the activation mechanism of safety in reasoning models.

Large Vision-Language Models (VLMs) have achieved remarkable performance across a wide range of tasks. However, their deployment in safety-critical domains poses significant challenges. Existing safety fine-tuning methods, which focus on textual or multimodal content, fall short in addressing challenging cases or disrupt the balance between helpfulness and harmlessness. Our evaluation highlights a safety reasoning gap: these methods lack safety visual reasoning ability, leading to such bottlenecks. To address this limitation and enhance both visual perception and reasoning in safety-critical contexts, we propose a novel dataset that integrates multi-image inputs with safety Chain-of-Thought (CoT) labels as fine-grained reasoning logic to improve model performance. Specifically, we introduce the Multi-Image Safety (MIS) dataset, an instruction-following dataset tailored for multi-image safety scenarios, consisting of training and test splits. Our experiments demonstrate that fine-tuning InternVL2.5-8B with MIS significantly outperforms both powerful open-source models and API-based models in challenging multi-image tasks requiring safety-related visual reasoning. This approach not only delivers exceptional safety performance but also preserves general capabilities without any trade-offs. Specifically, fine-tuning with MIS increases average accuracy by 0.83% across five general benchmarks and reduces the Attack Success Rate (ASR) on multiple safety benchmarks by a large margin. Data and Models are released under: https://dripnowhy.github.io/MIS/{https://dripnowhy.github.io/MIS/}

With the rapid development of large language models (LLMs), they are not only used as general-purpose AI assistants but are also customized through further fine-tuning to meet the requirements of different applications. A pivotal factor in the success of current LLMs is the alignment process. Current alignment methods, such as supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF), focus on training-time alignment and are often complex and cumbersome to implement. Therefore, we develop InferAligner, a novel inference-time alignment method that utilizes cross-model guidance for harmlessness alignment. InferAligner utilizes safety steering vectors extracted from safety-aligned model to modify the activations of the target model when responding to harmful inputs, thereby guiding the target model to provide harmless responses. Experimental results show that our method can be very effectively applied to domain-specific models in finance, medicine, and mathematics, as well as to multimodal large language models (MLLMs) such as LLaVA. It significantly diminishes the Attack Success Rate (ASR) of both harmful instructions and jailbreak attacks, while maintaining almost unchanged performance in downstream tasks.

Ensuring Large Language Model (LLM) safety remains challenging due to the absence of universal standards and reliable content validators, making it difficult to obtain effective training signals. We discover that aligned models already possess robust internal safety beliefs: they consistently produce high-confidence refusals to harmful requests while exhibiting high entropy when generating potentially dangerous content. This entropy gap reveals an untapped signal--models intrinsically "know" when to refuse. We introduce Safety Instincts Reinforcement Learning (SIRL), which transforms this internal confidence into a self-generated reward signal, eliminating dependence on external validators or human annotations. SIRL teaches models to trust their safety instincts by reinforcing low-entropy refusal behaviors. Evaluated on Llama and Qwen models, SIRL maintains 89%+ Defense Success Rates (DSRs) against 20+ jailbreak methods, from static prompts to adaptive attacks. Using only 15,000 unlabeled prompts, SIRL surpasses resource-intensive supervised methods while preserving performance on mathematics, coding, and conversation benchmarks. Our work demonstrates that effective alignment can emerge from within, paving the way for more autonomous and robust AI safety mechanisms that scale without extensive human oversight.

Large Vision-Language Models (LVLMs) have achieved impressive progress across various applications but remain vulnerable to malicious queries that exploit the visual modality. Existing alignment approaches typically fail to resist malicious queries while preserving utility on benign ones effectively. To address these challenges, we propose Deep Aligned Visual Safety Prompt (DAVSP), which is built upon two key innovations. First, we introduce the Visual Safety Prompt, which appends a trainable padding region around the input image. It preserves visual features and expands the optimization space. Second, we propose Deep Alignment, a novel approach to train the visual safety prompt through supervision in the model's activation space. It enhances the inherent ability of LVLMs to perceive malicious queries, achieving deeper alignment than prior works. Extensive experiments across five benchmarks on two representative LVLMs demonstrate that DAVSP effectively resists malicious queries while preserving benign input utility. Furthermore, DAVSP exhibits great cross-model generation ability. Ablation studies further reveal that both the Visual Safety Prompt and Deep Alignment are essential components, jointly contributing to its overall effectiveness. The code is publicly available at https://github.com/zhangyitonggg/DAVSP.

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

Large language models (LLMs) often demonstrate strong safety performance in high-resource languages, yet exhibit severe vulnerabilities when queried in low-resource languages. We attribute this gap to a mismatch between language-agnostic semantic understanding ability and language-dominant safety alignment biased toward high-resource languages. Consistent with this hypothesis, we empirically identify the semantic bottleneck in LLMs, an intermediate layer in which the geometry of model representations is governed primarily by shared semantic content rather than language identity. Building on this observation, we propose Language-Agnostic Semantic Alignment (LASA), which anchors safety alignment directly in semantic bottlenecks. Experiments show that LASA substantially improves safety across all languages: average attack success rate (ASR) drops from 24.7% to 2.8% on LLaMA-3.1-8B-Instruct and remains around 3-4% across Qwen2.5 and Qwen3 Instruct models (7B-32B). Together, our analysis and method offer a representation-level perspective on LLM safety, suggesting that safety alignment requires anchoring safety understanding not in surface text, but in the model's language-agnostic semantic space.

Text-to-Image (T2I) models have achieved remarkable success in generating visual content from text inputs. Although multiple safety alignment strategies have been proposed to prevent harmful outputs, they often lead to overly cautious behavior -- rejecting even benign prompts -- a phenomenon known as over-refusal that reduces the practical utility of T2I models. Despite over-refusal having been observed in practice, there is no large-scale benchmark that systematically evaluates this phenomenon for T2I models. In this paper, we present an automatic workflow to construct synthetic evaluation data, resulting in OVERT (OVEr-Refusal evaluation on Text-to-image models), the first large-scale benchmark for assessing over-refusal behaviors in T2I models. OVERT includes 4,600 seemingly harmful but benign prompts across nine safety-related categories, along with 1,785 genuinely harmful prompts (OVERT-unsafe) to evaluate the safety-utility trade-off. Using OVERT, we evaluate several leading T2I models and find that over-refusal is a widespread issue across various categories (Figure 1), underscoring the need for further research to enhance the safety alignment of T2I models without compromising their functionality. As a preliminary attempt to reduce over-refusal, we explore prompt rewriting; however, we find it often compromises faithfulness to the meaning of the original prompts. Finally, we demonstrate the flexibility of our generation framework in accommodating diverse safety requirements by generating customized evaluation data adapting to user-defined policies.

We introduce a low-resource safety enhancement method for aligning large language models (LLMs) without the need for supervised fine-tuning (SFT) or reinforcement learning from human feedback (RLHF). Our main idea is to exploit knowledge distillation to extract the alignment information from existing well-aligned LLMs and integrate it into unaligned LLMs in a plug-and-play fashion. Methodology, we employ delta debugging to identify the critical components of knowledge necessary for effective distillation. On the harmful question dataset, our method significantly enhances the average defense success rate by approximately 14.41%, reaching as high as 51.39%, in 17 unaligned pre-trained LLMs, without compromising performance.

Current safety alignment for large language models(LLMs) continues to present vulnerabilities, given that adversarial prompting can effectively bypass their safety measures.Our investigation shows that these safety mechanisms predominantly depend on a limited subset of attention heads: removing or ablating these heads can severely compromise model safety. To identify and evaluate these safety-critical components, we introduce RDSHA, a targeted ablation method that leverages the model's refusal direction to pinpoint attention heads mostly responsible for safety behaviors. Further analysis shows that existing jailbreak attacks exploit this concentration by selectively bypassing or manipulating these critical attention heads. To address this issue, we propose AHD, a novel training strategy designed to promote the distributed encoding of safety-related behaviors across numerous attention heads. Experimental results demonstrate that AHD successfully distributes safety-related capabilities across more attention heads. Moreover, evaluations under several mainstream jailbreak attacks show that models trained with AHD exhibit considerably stronger safety robustness, while maintaining overall functional utility.

The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that many of these vulnerabilities are related to a shared underlying issue: safety alignment can take shortcuts, wherein the alignment adapts a model's generative distribution primarily over only its very first few output tokens. We refer to this issue as shallow safety alignment. In this paper, we present case studies to explain why shallow safety alignment can exist and provide evidence that current aligned LLMs are subject to this issue. We also show how these findings help explain multiple recently discovered vulnerabilities in LLMs, including the susceptibility to adversarial suffix attacks, prefilling attacks, decoding parameter attacks, and fine-tuning attacks. Importantly, we discuss how this consolidated notion of shallow safety alignment sheds light on promising research directions for mitigating these vulnerabilities. For instance, we show that deepening the safety alignment beyond just the first few tokens can often meaningfully improve robustness against some common exploits. Finally, we design a regularized finetuning objective that makes the safety alignment more persistent against fine-tuning attacks by constraining updates on initial tokens. Overall, we advocate that future safety alignment should be made more than just a few tokens deep.

Most prior safety research of large language models (LLMs) has focused on enhancing the alignment of LLMs to better suit the safety requirements of humans. However, internalizing such safeguard features into larger models brought challenges of higher training cost and unintended degradation of helpfulness. To overcome such challenges, a modular approach employing a smaller LLM to detect harmful user queries is regarded as a convenient solution in designing LLM-based system with safety requirements. In this paper, we leverage a smaller LLM for both harmful query detection and safeguard response generation. We introduce our safety requirements and the taxonomy of harmfulness categories, and then propose a multi-task learning mechanism fusing the two tasks into a single model. We demonstrate the effectiveness of our approach, providing on par or surpassing harmful query detection and safeguard response performance compared to the publicly available LLMs.

In this work, we introduce the PKU-SafeRLHF dataset, designed to promote research on safety alignment in large language models (LLMs). As a sibling project to SafeRLHF and BeaverTails, we separate annotations of helpfulness and harmlessness for question-answering pairs, providing distinct perspectives on these coupled attributes. Overall, we provide 44.6k refined prompts and 265k question-answer pairs with safety meta-labels for 19 harm categories and three severity levels ranging from minor to severe, with answers generated by Llama-family models. Based on this, we collected 166.8k preference data, including dual-preference (helpfulness and harmlessness decoupled) and single-preference data (trade-off the helpfulness and harmlessness from scratch), respectively. Using the large-scale annotation data, we further train severity-sensitive moderation for the risk control of LLMs and safety-centric RLHF algorithms for the safety alignment of LLMs. We believe this dataset will be a valuable resource for the community, aiding in the safe deployment of LLMs.

Optimizing large language models (LLMs) for downstream use cases often involves the customization of pre-trained LLMs through further fine-tuning. Meta's open release of Llama models and OpenAI's APIs for fine-tuning GPT-3.5 Turbo on custom datasets also encourage this practice. But, what are the safety costs associated with such custom fine-tuning? We note that while existing safety alignment infrastructures can restrict harmful behaviors of LLMs at inference time, they do not cover safety risks when fine-tuning privileges are extended to end-users. Our red teaming studies find that the safety alignment of LLMs can be compromised by fine-tuning with only a few adversarially designed training examples. For instance, we jailbreak GPT-3.5 Turbo's safety guardrails by fine-tuning it on only 10 such examples at a cost of less than $0.20 via OpenAI's APIs, making the model responsive to nearly any harmful instructions. Disconcertingly, our research also reveals that, even without malicious intent, simply fine-tuning with benign and commonly used datasets can also inadvertently degrade the safety alignment of LLMs, though to a lesser extent. These findings suggest that fine-tuning aligned LLMs introduces new safety risks that current safety infrastructures fall short of addressing -- even if a model's initial safety alignment is impeccable, it is not necessarily to be maintained after custom fine-tuning. We outline and critically analyze potential mitigations and advocate for further research efforts toward reinforcing safety protocols for the custom fine-tuning of aligned LLMs.

Multimodal Large Language Models are increasingly adopted as autonomous agents in interactive environments, yet their ability to proactively address safety hazards remains insufficient. We introduce SafetyALFRED, built upon the embodied agent benchmark ALFRED, augmented with six categories of real-world kitchen hazards. While existing safety evaluations focus on hazard recognition through disembodied question answering (QA) settings, we evaluate eleven state-of-the-art models from the Qwen, Gemma, and Gemini families on not only hazard recognition, but also active risk mitigation through embodied planning. Our experimental results reveal a significant alignment gap: while models can accurately recognize hazards in QA settings, average mitigation success rates for these hazards are low in comparison. Our findings demonstrate that static evaluations through QA are insufficient for physical safety, thus we advocate for a paradigm shift toward benchmarks that prioritize corrective actions in embodied contexts. We open-source our code and dataset under https://github.com/sled-group/SafetyALFRED.git

Safety alignment is critical for the responsible deployment of large language models (LLMs). As Mixture-of-Experts (MoE) architectures are increasingly adopted to scale model capacity, understanding their safety robustness becomes essential. Existing adversarial attacks, however, have notable limitations. Prompt-based jailbreaks rely on heuristic search and transfer poorly, model intervention methods require privileged access to internal representations, and optimization-based input attacks remain output-centric and are fundamentally limited to MoE models due to the non-differentiable routing mechanism. In this paper, we present RouteHijack, a routing-aware jailbreak for MoE LLMs. Our key insight is that safety behavior is concentrated in a small subset of experts, creating an opportunity to steer model behavior by influencing routing decisions through input optimization. Building on this observation, RouteHijack first performs response-driven expert localization to identify safety-critical and harmful experts by contrasting activations under safe refusals and harmful completions. It then constructs adversarial suffixes with a routing-aware objective that suppresses safety experts, promotes harmful experts, and prevents early-stage refusal during generation. At inference time, the optimized suffix is appended to a malicious prompt, requiring only input access. Across seven MoE LLMs, RouteHijack achieves a 69.3\% average attack success rate (ASR), outperforming prior optimization-based attack by 3.2times. RouteHijack also transfers zero-shot across five sibling MoE variants, raising average ASR from 27.7\% to 61.2\%, and further generalizes to three MoE-based VLMs, increasing average ASR from 2.47\% to 38.7\%. These findings expose a fundamental vulnerability in sparse expert architectures and highlight the need for defenses beyond output-level alignment.

Although Large Reasoning Models (LRMs) have progressed in solving complex problems, their chain-of-thought (CoT) reasoning often contains harmful content that can persist even when the final responses appear safe. We show that this issue still remains in existing methods which overlook the unique significance of safe reasoning, undermining their trustworthiness and posing potential risks in applications if unsafe reasoning is accessible for and exploited by malicious users. We therefore shift our focus to aligning the safety of reasoning itself in this paper and explore process supervision as the solution. However, simply rewarding safe reasoning proves inadequate due to low rollout diversity and limited training signals. To tackle this challenge, we first delve into the characteristics of safe reasoning and uncover several critical insights that 1) safe reasoning is often consolidated by a few critical steps of safety triggers; 2) compliance cues strongly correlate with unsafe continuations; and 3) corrective interventions reliably steer unsafe trajectories towards safer traces. Motivated by these, we propose Intervened Preference Optimization (IPO), an alignment method that enforces safe reasoning by substituting compliance steps with safety triggers and constructing pairs for preference learning with strong signals. Experiments on jailbreak and adversarial safety benchmarks demonstrate that IPO remarkably improves overall safety regarding both reasoning and responses, outperforming SFT-based and RL-based baselines with a relative reduction of over 30% in harmfulness, while preserving excellent performance across diverse reasoning tasks. The results highlight the importance of explicit alignment for reasoning and provide a practical path to safer LRMs.

Aligned language models face a significant limitation as their fine-tuning often results in compromised safety. To tackle this, we propose a simple method RESTA that performs LLM safety realignment. RESTA stands for REstoring Safety through Task Arithmetic. At its core, it involves a simple arithmetic addition of a safety vector to the weights of the compromised model. We demonstrate the effectiveness of RESTA in both parameter-efficient and full fine-tuning, covering a wide range of downstream tasks, including instruction following in Chinese, English, and Hindi, as well as problem-solving capabilities in Code and Math. We also showcase the generalizability of RESTA on three existing safety evaluation benchmarks and a multilingual benchmark dataset proposed as a part of this work, consisting of 550 harmful questions covering 11 categories, each with 5 sub-categories of harm. Overall, RESTA decreases the harmfulness of the compromised model from 18.6% to 5.1% and from 9.2% to 1.5% in parameter-efficient and full fine-tuning, respectively, while maintaining most of the model's performance on the task. We release the source codes at: https://github.com/declare-lab/resta.

LLM-based agents are becoming increasingly proficient at solving web-based tasks. With this capability comes a greater risk of misuse for malicious purposes, such as posting misinformation in an online forum or selling illicit substances on a website. To evaluate these risks, we propose SafeArena, the first benchmark to focus on the deliberate misuse of web agents. SafeArena comprises 250 safe and 250 harmful tasks across four websites. We classify the harmful tasks into five harm categories -- misinformation, illegal activity, harassment, cybercrime, and social bias, designed to assess realistic misuses of web agents. We evaluate leading LLM-based web agents, including GPT-4o, Claude-3.5 Sonnet, Qwen-2-VL 72B, and Llama-3.2 90B, on our benchmark. To systematically assess their susceptibility to harmful tasks, we introduce the Agent Risk Assessment framework that categorizes agent behavior across four risk levels. We find agents are surprisingly compliant with malicious requests, with GPT-4o and Qwen-2 completing 34.7% and 27.3% of harmful requests, respectively. Our findings highlight the urgent need for safety alignment procedures for web agents. Our benchmark is available here: https://safearena.github.io

Current vision large language models (VLLMs) exhibit remarkable capabilities yet are prone to generate harmful content and are vulnerable to even the simplest jailbreaking attacks. Our initial analysis finds that this is due to the presence of harmful data during vision-language instruction fine-tuning, and that VLLM fine-tuning can cause forgetting of safety alignment previously learned by the underpinning LLM. To address this issue, we first curate a vision-language safe instruction-following dataset VLGuard covering various harmful categories. Our experiments demonstrate that integrating this dataset into standard vision-language fine-tuning or utilizing it for post-hoc fine-tuning effectively safety aligns VLLMs. This alignment is achieved with minimal impact on, or even enhancement of, the models' helpfulness. The versatility of our safety fine-tuning dataset makes it a valuable resource for safety-testing existing VLLMs, training new models or safeguarding pre-trained VLLMs. Empirical results demonstrate that fine-tuned VLLMs effectively reject unsafe instructions and substantially reduce the success rates of several black-box adversarial attacks, which approach zero in many cases. The code and dataset are available at https://github.com/ys-zong/VLGuard.

Large language models (LLMs) undergo safety alignment to ensure safe conversations with humans. However, this paper introduces a training-free attack method capable of reversing safety alignment, converting the outcomes of stronger alignment into greater potential for harm by accessing only LLM output token distributions. Specifically, our method achieves this reversal by contrasting the output token distribution of a safety-aligned language model (e.g., Llama-2-chat) against its pre-trained version (e.g., Llama-2), so that the token predictions are shifted towards the opposite direction of safety alignment. We name this method emulated disalignment (ED) because sampling from this contrastive distribution provably emulates the result of fine-tuning to minimize a safety reward. Our experiments with ED across three evaluation datasets and four model families (Llama-1, Llama-2, Mistral, and Alpaca) show that ED doubles the harmfulness of pre-trained models and outperforms strong baselines, achieving the highest harmful rates in 43 out of 48 evaluation subsets by a large margin. Eventually, given ED's reliance on language model output token distributions, which particularly compromises open-source models, our findings highlight the need to reassess the open accessibility of language models, even if they have been safety-aligned. Code is available at https://github.com/ZHZisZZ/emulated-disalignment.

Merging Large Language Models (LLMs) is a cost-effective technique for combining multiple expert LLMs into a single versatile model, retaining the expertise of the original ones. However, current approaches often overlook the importance of safety alignment during merging, leading to highly misaligned models. This work investigates the effects of model merging on alignment. We evaluate several popular model merging techniques, demonstrating that existing methods do not only transfer domain expertise but also propagate misalignment. We propose a simple two-step approach to address this problem: (i) generating synthetic safety and domain-specific data, and (ii) incorporating these generated data into the optimization process of existing data-aware model merging techniques. This allows us to treat alignment as a skill that can be maximized in the resulting merged LLM. Our experiments illustrate the effectiveness of integrating alignment-related data during merging, resulting in models that excel in both domain expertise and alignment.

Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial training: generating adversarial prompts and fine-tuning LMs to defend against them. We introduce a different paradigm: framing safety alignment as a non-zero-sum game between an Attacker LM and a Defender LM trained jointly via online reinforcement learning. Each LM continuously adapts to the other's evolving strategies, driving iterative improvement. Our method uses a preference-based reward signal derived from pairwise comparisons instead of point-wise scores, providing more robust supervision and potentially reducing reward hacking. Our RL recipe, AdvGame, shifts the Pareto frontier of safety and utility, yielding a Defender LM that is simultaneously more helpful and more resilient to adversarial attacks. In addition, the resulting Attacker LM converges into a strong, general-purpose red-teaming agent that can be directly deployed to probe arbitrary target models.

Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, such as accessing files or entering credentials, can cause irreversible harm. Existing alignment methods, largely optimized for static generation and task completion, break down in these settings due to sequential decision-making, adversarial tool feedback, and overconfident intermediate reasoning. We introduce MOSAIC, a post-training framework that aligns agents for safe multi-step tool use by making safety decisions explicit and learnable. MOSAIC structures inference as a plan, check, then act or refuse loop, with explicit safety reasoning and refusal as first-class actions. To train without trajectory-level labels, we use preference-based reinforcement learning with pairwise trajectory comparisons, which captures safety distinctions often missed by scalar rewards. We evaluate MOSAIC zero-shot across three model families, Qwen2.5-7B, Qwen3-4B-Thinking, and Phi-4, and across out-of-distribution benchmarks spanning harmful tasks, prompt injection, benign tool use, and cross-domain privacy leakage. MOSAIC reduces harmful behavior by up to 50%, increases harmful-task refusal by over 20% on injection attacks, cuts privacy leakage, and preserves or improves benign task performance, demonstrating robust generalization across models, domains, and agentic settings.

With the widespread application of Large Language Models (LLMs), it has become a significant concern to ensure their safety and prevent harmful responses. While current safe-alignment methods based on instruction fine-tuning and Reinforcement Learning from Human Feedback (RLHF) can effectively reduce harmful responses from LLMs, they often require high-quality datasets and heavy computational overhead during model training. Another way to align language models is to modify the logit of tokens in model outputs without heavy training. Recent studies have shown that contrastive decoding can enhance the performance of language models by reducing the likelihood of confused tokens. However, these methods require the manual selection of contrastive models or instruction templates. To this end, we propose Adversarial Contrastive Decoding (ACD), an optimization-based framework to generate two opposite system prompts for prompt-based contrastive decoding. ACD only needs to apply a lightweight prompt tuning on a rather small anchor dataset (< 3 min for each model) without training the target model. Experiments conducted on extensive models and benchmarks demonstrate that the proposed method achieves much better safety performance than previous model training-free decoding methods without sacrificing its original generation ability.

Recent work discovered Emergent Misalignment (EM): fine-tuning large language models on narrowly harmful datasets can lead them to become broadly misaligned. A survey of experts prior to publication revealed this was highly unexpected, demonstrating critical gaps in our understanding of model alignment. In this work, we both advance understanding and provide tools for future research. Using new narrowly misaligned datasets, we create a set of improved model organisms that achieve 99% coherence (vs. 67% prior), work with smaller 0.5B parameter models (vs. 32B), and that induce misalignment using a single rank-1 LoRA adapter. We demonstrate that EM occurs robustly across diverse model sizes, three model families, and numerous training protocols including full supervised fine-tuning. Leveraging these cleaner model organisms, we isolate a mechanistic phase transition and demonstrate that it corresponds to a robust behavioural phase transition in all studied organisms. Aligning large language models is critical for frontier AI safety, yet EM exposes how far we are from achieving this robustly. By distilling clean model organisms that isolate a minimal alignment-compromising change, and where this is learnt, we establish a foundation for future research into understanding and mitigating alignment risks in LLMs.

Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to LLMs form Vision Language Models (VLMs). However, recent research shows that the visual modality in VLMs is highly vulnerable, allowing attackers to bypass safety alignment in LLMs through visually transmitted content, launching harmful attacks. To address this challenge, we propose a progressive concept-based alignment strategy, PSA-VLM, which incorporates safety modules as concept bottlenecks to enhance visual modality safety alignment. By aligning model predictions with specific safety concepts, we improve defenses against risky images, enhancing explainability and controllability while minimally impacting general performance. Our method is obtained through two-stage training. The low computational cost of the first stage brings very effective performance improvement, and the fine-tuning of the language model in the second stage further improves the safety performance. Our method achieves state-of-the-art results on popular VLM safety benchmark.

Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities, yet their expanded modality space introduces new compositional safety risks that emerge from complex text-image interactions. Such cross-modal couplings can produce unsafe semantics even when individual inputs are benign, exposing the fragile safety awareness of current MLLMs. While recent works enhance safety by guiding models to reason about potential risks, unregulated reasoning traces may compromise alignment; although Group Relative Policy Optimization (GRPO) offers self-rewarded refinement without human supervision, it lacks verifiable signals for reasoning safety. To address this, we propose SafeGRPO a self-rewarded multimodal safety alignment framework that integrates rule-governed reward construction into GRPO, enabling interpretable and verifiable optimization of reasoning safety. Built upon the constructed SafeTag-VL-3K dataset with explicit visual, textual, and combined safety tags, SafeGRPO performs step-guided safety thinking to enforce structured reasoning and behavior alignment, substantially improving multimodal safety awareness, compositional robustness, and reasoning stability across diverse benchmarks without sacrificing general capabilities.

As Large Language Models (LLMs) and generative AI become more widespread, the content safety risks associated with their use also increase. We find a notable deficiency in high-quality content safety datasets and benchmarks that comprehensively cover a wide range of critical safety areas. To address this, we define a broad content safety risk taxonomy, comprising 13 critical risk and 9 sparse risk categories. Additionally, we curate AEGISSAFETYDATASET, a new dataset of approximately 26, 000 human-LLM interaction instances, complete with human annotations adhering to the taxonomy. We plan to release this dataset to the community to further research and to help benchmark LLM models for safety. To demonstrate the effectiveness of the dataset, we instruction-tune multiple LLM-based safety models. We show that our models (named AEGISSAFETYEXPERTS), not only surpass or perform competitively with the state-of-the-art LLM-based safety models and general purpose LLMs, but also exhibit robustness across multiple jail-break attack categories. We also show how using AEGISSAFETYDATASET during the LLM alignment phase does not negatively impact the performance of the aligned models on MT Bench scores. Furthermore, we propose AEGIS, a novel application of a no-regret online adaptation framework with strong theoretical guarantees, to perform content moderation with an ensemble of LLM content safety experts in deployment

As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values has become a paramount concern. Current safety benchmarks primarily evaluate whether agents refuse explicitly harmful instructions or whether they can maintain procedural compliance in complex tasks. However, there is a lack of benchmarks designed to capture emergent forms of outcome-driven constraint violations, which arise when agents pursue goal optimization under strong performance incentives while deprioritizing ethical, legal, or safety constraints over multiple steps in realistic production settings. To address this gap, we introduce a new benchmark comprising 40 distinct scenarios. Each scenario presents a task that requires multi-step actions, and the agent's performance is tied to a specific Key Performance Indicator (KPI). Each scenario features Mandated (instruction-commanded) and Incentivized (KPI-pressure-driven) variations to distinguish between obedience and emergent misalignment. Across 12 state-of-the-art large language models, we observe outcome-driven constraint violations ranging from 1.3% to 71.4%, with 9 of the 12 evaluated models exhibiting misalignment rates between 30% and 50%. Strikingly, we find that superior reasoning capability does not inherently ensure safety; for instance, Gemini-3-Pro-Preview, one of the most capable models evaluated, exhibits the highest violation rate at 71.4%, frequently escalating to severe misconduct to satisfy KPIs. Furthermore, we observe significant "deliberative misalignment", where the models that power the agents recognize their actions as unethical during separate evaluation. These results emphasize the critical need for more realistic agentic-safety training before deployment to mitigate their risks in the real world.

As Large Language Models (LLMs) continue to advance in understanding and generating long sequences, new safety concerns have been introduced through the long context. However, the safety of LLMs in long-context tasks remains under-explored, leaving a significant gap in both evaluation and improvement of their safety. To address this, we introduce LongSafety, the first comprehensive benchmark specifically designed to evaluate LLM safety in open-ended long-context tasks. LongSafety encompasses 7 categories of safety issues and 6 user-oriented long-context tasks, with a total of 1,543 test cases, averaging 5,424 words per context. Our evaluation towards 16 representative LLMs reveals significant safety vulnerabilities, with most models achieving safety rates below 55%. Our findings also indicate that strong safety performance in short-context scenarios does not necessarily correlate with safety in long-context tasks, emphasizing the unique challenges and urgency of improving long-context safety. Moreover, through extensive analysis, we identify challenging safety issues and task types for long-context models. Furthermore, we find that relevant context and extended input sequences can exacerbate safety risks in long-context scenarios, highlighting the critical need for ongoing attention to long-context safety challenges. Our code and data are available at https://github.com/thu-coai/LongSafety.

As Multimodal Large Language Models (MLLMs) acquire stronger reasoning capabilities to handle complex, multi-image instructions, this advancement may pose new safety risks. We study this problem by introducing MIR-SafetyBench, the first benchmark focused on multi-image reasoning safety, which consists of 2,676 instances across a taxonomy of 9 multi-image relations. Our extensive evaluations on 19 MLLMs reveal a troubling trend: models with more advanced multi-image reasoning can be more vulnerable on MIR-SafetyBench. Beyond attack success rates, we find that many responses labeled as safe are superficial, often driven by misunderstanding or evasive, non-committal replies. We further observe that unsafe generations exhibit lower attention entropy than safe ones on average. This internal signature suggests a possible risk that models may over-focus on task solving while neglecting safety constraints. Our code and data are available at https://github.com/thu-coai/MIR-SafetyBench.

Large Language Models (LLMs) need to be aligned with human expectations to ensure their safety and utility in most applications. Alignment is challenging, costly, and needs to be repeated for every LLM and alignment criterion. We propose to decouple LLMs and alignment by training aligner models that can be used to align any LLM for a given criteria on an as-needed basis, thus also reducing the potential negative impacts of alignment on performance. Our recipe for training the aligner models solely relies on synthetic data generated with a (prompted) LLM and can be easily adjusted for a variety of alignment criteria. We illustrate our method by training an "ethical" aligner and verify its efficacy empirically.

Large language models (LLMs) achieve state-of-the-art performance on multiple language tasks, yet their safety guardrails can be circumvented, leading to harmful generations. In light of this, recent research on safety mechanisms has emerged, revealing that when safety representations or component are suppressed, the safety capability of LLMs are compromised. However, existing research tends to overlook the safety impact of multi-head attention mechanisms, despite their crucial role in various model functionalities. Hence, in this paper, we aim to explore the connection between standard attention mechanisms and safety capability to fill this gap in the safety-related mechanistic interpretability. We propose a novel metric which tailored for multi-head attention, the Safety Head ImPortant Score (Ships), to assess the individual heads' contributions to model safety. Based on this, we generalize Ships to the dataset level and further introduce the Safety Attention Head AttRibution Algorithm (Sahara) to attribute the critical safety attention heads inside the model. Our findings show that the special attention head has a significant impact on safety. Ablating a single safety head allows aligned model (e.g., Llama-2-7b-chat) to respond to 16 times more harmful queries, while only modifying 0.006% of the parameters, in contrast to the ~ 5% modification required in previous studies. More importantly, we demonstrate that attention heads primarily function as feature extractors for safety and models fine-tuned from the same base model exhibit overlapping safety heads through comprehensive experiments. Together, our attribution approach and findings provide a novel perspective for unpacking the black box of safety mechanisms within large models.

Recent innovations in language model training have demonstrated that it is possible to create highly performant models that are small enough to run on a smartphone. As these models are deployed in an increasing number of domains, it is critical to ensure that they are aligned with human preferences and safety considerations. In this report, we present our methodology for safety aligning the Phi-3 series of language models. We utilized a "break-fix" cycle, performing multiple rounds of dataset curation, safety post-training, benchmarking, red teaming, and vulnerability identification to cover a variety of harm areas in both single and multi-turn scenarios. Our results indicate that this approach iteratively improved the performance of the Phi-3 models across a wide range of responsible AI benchmarks.

Big models, exemplified by Large Language Models (LLMs), are models typically pre-trained on massive data and comprised of enormous parameters, which not only obtain significantly improved performance across diverse tasks but also present emergent capabilities absent in smaller models. However, the growing intertwining of big models with everyday human lives poses potential risks and might cause serious social harm. Therefore, many efforts have been made to align LLMs with humans to make them better follow user instructions and satisfy human preferences. Nevertheless, `what to align with' has not been fully discussed, and inappropriate alignment goals might even backfire. In this paper, we conduct a comprehensive survey of different alignment goals in existing work and trace their evolution paths to help identify the most essential goal. Particularly, we investigate related works from two perspectives: the definition of alignment goals and alignment evaluation. Our analysis encompasses three distinct levels of alignment goals and reveals a goal transformation from fundamental abilities to value orientation, indicating the potential of intrinsic human values as the alignment goal for enhanced LLMs. Based on such results, we further discuss the challenges of achieving such intrinsic value alignment and provide a collection of available resources for future research on the alignment of big models.

Deep Research (DR) agents built on Large Language Models (LLMs) can perform complex, multi-step research by decomposing tasks, retrieving online information, and synthesizing detailed reports. However, the misuse of LLMs with such powerful capabilities can lead to even greater risks. This is especially concerning in high-stakes and knowledge-intensive domains such as biosecurity, where DR can generate a professional report containing detailed forbidden knowledge. Unfortunately, we have found such risks in practice: simply submitting a harmful query, which a standalone LLM directly rejects, can elicit a detailed and dangerous report from DR agents. This highlights the elevated risks and underscores the need for a deeper safety analysis. Yet, jailbreak methods designed for LLMs fall short in exposing such unique risks, as they do not target the research ability of DR agents. To address this gap, we propose two novel jailbreak strategies: Plan Injection, which injects malicious sub-goals into the agent's plan; and Intent Hijack, which reframes harmful queries as academic research questions. We conducted extensive experiments across different LLMs and various safety benchmarks, including general and biosecurity forbidden prompts. These experiments reveal 3 key findings: (1) Alignment of the LLMs often fail in DR agents, where harmful prompts framed in academic terms can hijack agent intent; (2) Multi-step planning and execution weaken the alignment, revealing systemic vulnerabilities that prompt-level safeguards cannot address; (3) DR agents not only bypass refusals but also produce more coherent, professional, and dangerous content, compared with standalone LLMs. These results demonstrate a fundamental misalignment in DR agents and call for better alignment techniques tailored to DR agents. Code and datasets are available at https://chenxshuo.github.io/deeper-harm.

Even highly capable large language models (LLMs) can produce biased or unsafe responses, and alignment techniques, such as RLHF, aimed at mitigating this issue, are expensive and prone to overfitting as they retrain the LLM. This paper introduces a novel inference-time alignment approach that ensures LLMs generate safe responses almost surely, i.e., with a probability approaching one. We achieve this by framing the safe generation of inference-time responses as a constrained Markov decision process within the LLM's latent space. Crucially, we augment a safety state that tracks the evolution of safety constraints and enables us to demonstrate formal safety guarantees upon solving the MDP in the latent space. Building on this foundation, we propose InferenceGuard, a practical implementation that safely aligns LLMs without modifying the model weights. Empirically, we demonstrate InferenceGuard effectively balances safety and task performance, outperforming existing inference-time alignment methods in generating safe and aligned responses.

Unlimited, or so-called helpful-only language models are trained without safety alignment constraints and never refuse user queries. They are widely used by leading AI companies as internal tools for red teaming and alignment evaluation. For example, if a safety-aligned model produces harmful outputs similar to an unlimited model, this indicates alignment failures that require further attention. Despite their essential role in assessing alignment, such models are not available to the research community. We introduce Jinx, a helpful-only variant of popular open-weight LLMs. Jinx responds to all queries without refusals or safety filtering, while preserving the base model's capabilities in reasoning and instruction following. It provides researchers with an accessible tool for probing alignment failures, evaluating safety boundaries, and systematically studying failure modes in language model safety.

Large Reasoning Models (LRMs) have become powerful tools for complex problem solving, but their structured reasoning pathways can lead to unsafe outputs when exposed to harmful prompts. Existing safety alignment methods reduce harmful outputs but can degrade reasoning depth, leading to significant trade-offs in complex, multi-step tasks, and remain vulnerable to sophisticated jailbreak attacks. To address this, we introduce SAFEPATH, a lightweight alignment method that fine-tunes LRMs to emit a short, 8-token Safety Primer at the start of their reasoning, in response to harmful prompts, while leaving the rest of the reasoning process unsupervised. Empirical results across multiple benchmarks indicate that SAFEPATH effectively reduces harmful outputs while maintaining reasoning performance. Specifically, SAFEPATH reduces harmful responses by up to 90.0% and blocks 83.3% of jailbreak attempts in the DeepSeek-R1-Distill-Llama-8B model, while requiring 295.9x less compute than Direct Refusal and 314.1x less than SafeChain. We further introduce a zero-shot variant that requires no fine-tuning. In addition, we provide a comprehensive analysis of how existing methods in LLMs generalize, or fail, when applied to reasoning-centric models, revealing critical gaps and new directions for safer AI.