{"total":387,"rows":[{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917,"area":null},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154,"area":"alignment"},{"id":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711,"area":null},{"id":"2406.18495","title":"WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs","created":"2024-06-26","cited_by_count":496,"area":"safety"},{"id":"2310.02949","title":"Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models","created":"2023-10-04","cited_by_count":297,"area":"alignment"},{"id":"2401.10019","title":"R-Judge: Benchmarking Safety Risk Awareness for LLM Agents","created":"2024-01-18","cited_by_count":288,"area":"agents"},{"id":"2311.17600","title":"MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models","created":"2023-11-29","cited_by_count":274,"area":"mllm"},{"id":"2311.06668","title":"In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering","created":"2023-11-11","cited_by_count":245,"area":null},{"id":"2405.20947","title":"OR-Bench: An Over-Refusal Benchmark for Large Language Models","created":"2024-05-31","cited_by_count":244,"area":"alignment"},{"id":"2406.14598","title":"SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal","created":"2024-06-20","cited_by_count":240,"area":"alignment"},{"id":"2407.04295","title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","created":"2024-07-05","cited_by_count":230,"area":"safety"},{"id":"2309.13788","title":"Can LLM-Generated Misinformation Be Detected?","created":"2023-09-25","cited_by_count":177,"area":null},{"id":"2402.02207","title":"Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models","created":"2024-02-03","cited_by_count":167,"area":"safety"},{"id":"2408.17003","title":"Safety Layers in Aligned Large Language Models: The Key to LLM Security","created":"2024-08-30","cited_by_count":134,"area":"alignment"},{"id":"2501.09004","title":"Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails","created":"2025-01-15","cited_by_count":132,"area":"safety"},{"id":"2402.09283","title":"Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey","created":"2024-02-14","cited_by_count":130,"area":null},{"id":"2405.16833","title":"Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models","created":"2024-05-27","cited_by_count":125,"area":null},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2402.01109","title":"Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack","created":"2024-02-02","cited_by_count":115,"area":"alignment"},{"id":"2411.01111","title":"Rule Based Rewards for Language Model Safety","created":"2024-11-02","cited_by_count":108,"area":"alignment"},{"id":"2402.19085","title":"Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment","created":"2024-02-29","cited_by_count":107,"area":"alignment"},{"id":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105,"area":null},{"id":"2402.13669","title":"Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning","created":"2024-02-21","cited_by_count":96,"area":"distill"},{"id":"2402.18540","title":"Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates","created":"2024-02-28","cited_by_count":96,"area":null},{"id":"2405.18641","title":"Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack","created":"2024-05-28","cited_by_count":92,"area":"alignment"},{"id":"2409.01586","title":"Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation","created":"2024-09-03","cited_by_count":92,"area":null},{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90,"area":"alignment"},{"id":"2507.11878","title":"LLMs Encode Harmfulness and Refusal Separately","created":"2025-07-16","cited_by_count":88,"area":"safety"},{"id":"2401.11206","title":"InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance","created":"2024-01-20","cited_by_count":83,"area":"alignment"},{"id":"2406.20053","title":"Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation","created":"2024-06-28","cited_by_count":80,"area":null},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78,"area":"safety"},{"id":"2404.05399","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","created":"2024-04-08","cited_by_count":77,"area":"safety"},{"id":"2408.09600","title":"Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning","created":"2024-08-18","cited_by_count":72,"area":"alignment"},{"id":"2406.18682","title":"The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm","created":"2024-06-26","cited_by_count":70,"area":"safety"},{"id":"2403.15246","title":"FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions","created":"2024-03-22","cited_by_count":69,"area":null},{"id":"2407.09121","title":"Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training","created":"2024-07-12","cited_by_count":69,"area":null},{"id":"2402.09091","title":"Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues","created":"2024-02-14","cited_by_count":68,"area":"safety"},{"id":"2504.01903","title":"STAR-1: Safer Alignment of Reasoning LLMs with 1K Data","created":"2025-04-02","cited_by_count":68,"area":"lr"},{"id":"2401.00287","title":"The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness","created":"2023-12-30","cited_by_count":67,"area":null},{"id":"2402.06255","title":"Fight Back Against Jailbreaking via Prompt Adversarial Tuning","created":"2024-02-09","cited_by_count":67,"area":"safety"},{"id":"2310.06762","title":"TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models","created":"2023-10-10","cited_by_count":66,"area":"alignment"},{"id":"2410.07471","title":"SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection","created":"2024-10-09","cited_by_count":64,"area":null},{"id":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"area":null},{"id":"2406.17092","title":"BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models","created":"2024-06-24","cited_by_count":58,"area":"safety"},{"id":"2505.08054","title":"FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning","created":"2025-05-12","cited_by_count":58,"area":"lr"},{"id":"2405.18540","title":"Learning diverse attacks on large language models for robust red-teaming and safety tuning","created":"2024-05-28","cited_by_count":54,"area":"safety"},{"id":"2508.09224","title":"From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training","created":"2025-08-12","cited_by_count":52,"area":null},{"id":"2406.09324","title":"Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs","created":"2024-06-13","cited_by_count":51,"area":"safety"},{"id":"2512.10675","title":"Evaluating Gemini Robotics Policies in a Veo World Simulator","created":"2025-12-11","cited_by_count":51,"area":"wm"},{"id":"2408.11491","title":"SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering","created":"2024-08-21","cited_by_count":50,"area":"alignment"},{"id":"2402.04247","title":"Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy","created":"2024-02-06","cited_by_count":49,"area":null},{"id":"2410.03415","title":"Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation","created":"2024-10-04","cited_by_count":48,"area":null},{"id":"2410.12855","title":"JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework","created":"2024-10-11","cited_by_count":47,"area":"agents"},{"id":"2405.17374","title":"Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models","created":"2024-05-27","cited_by_count":46,"area":"alignment"},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2403.03744","title":"MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models","created":"2024-03-06","cited_by_count":44,"area":null},{"id":"2403.04786","title":"Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models","created":"2024-03-03","cited_by_count":44,"area":null},{"id":"2504.16980","title":"Safety Pretraining: Toward the Next Generation of Safe AI","created":"2025-04-23","cited_by_count":43,"area":null},{"id":"2506.07468","title":"Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models","created":"2025-06-09","cited_by_count":39,"area":"alignment"},{"id":"2505.17306","title":"Refusal Direction is Universal Across Safety-Aligned Languages","created":"2025-05-22","cited_by_count":38,"area":null},{"id":"2410.09760","title":"Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation","created":"2024-10-13","cited_by_count":37,"area":"alignment"},{"id":"2410.23861","title":"Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models","created":"2024-10-31","cited_by_count":37,"area":"mllm"},{"id":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36,"area":"alignment"},{"id":"2406.07243","title":"MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs","created":"2024-06-11","cited_by_count":35,"area":null},{"id":"2409.00598","title":"Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models","created":"2024-09-01","cited_by_count":35,"area":"alignment"},{"id":"2410.10014","title":"Safety-Aware Fine-Tuning of Large Language Models","created":"2024-10-13","cited_by_count":34,"area":null},{"id":"2502.12970","title":"Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking","created":"2025-02-18","cited_by_count":34,"area":"lr"},{"id":"2407.03963","title":"LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs","created":"2024-07-04","cited_by_count":33,"area":null},{"id":"2502.15851","title":"Control Illusion: The Failure of Instruction Hierarchies in Large Language Models","created":"2025-02-21","cited_by_count":33,"area":null},{"id":"2407.13833","title":"Phi-3 Safety Post-Training: Aligning Language Models with a \"Break-Fix\" Cycle","created":"2024-07-18","cited_by_count":32,"area":"alignment"},{"id":"2409.14586","title":"Backtracking Improves Generation Safety","created":"2024-09-22","cited_by_count":32,"area":"alignment"},{"id":"2411.09259","title":"Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey","created":"2024-11-14","cited_by_count":32,"area":"safety"},{"id":"2404.11049","title":"Stepwise Alignment for Constrained Language Model Policy Optimization","created":"2024-04-17","cited_by_count":30,"area":"alignment"},{"id":"2405.16229","title":"No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks","created":"2024-05-25","cited_by_count":29,"area":"alignment"},{"id":"2407.02855","title":"From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks","created":"2024-07-03","cited_by_count":29,"area":"safety"},{"id":"2401.16332","title":"Tradeoffs Between Alignment and Helpfulness in Language Models with Steering Methods","created":"2024-01-29","cited_by_count":28,"area":"alignment"},{"id":"2410.20971","title":"BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks","created":"2024-10-28","cited_by_count":28,"area":"mllm"},{"id":"2406.11852","title":"Risks from Language Models for Automated Mental Healthcare: Ethics and Structure for Implementation","created":"2024-04-02","cited_by_count":27,"area":null},{"id":"2410.01518","title":"InfiniPot: Infinite Context Processing on Memory-Constrained LLMs","created":"2024-10-02","cited_by_count":27,"area":null},{"id":"2506.13666","title":"We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems","created":"2025-06-16","cited_by_count":27,"area":"agents"},{"id":"2504.09420","title":"SaRO: Enhancing LLM Safety through Reasoning-based Alignment","created":"2025-04-13","cited_by_count":26,"area":"lr"},{"id":"2507.19227","title":"Jailbreaking Large Language Diffusion Models: Revealing Hidden Safety Flaws in Diffusion-Based Text Generation","created":"2025-07-25","cited_by_count":26,"area":"lr"},{"id":"2503.17239","title":"SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging","created":"2025-03-21","cited_by_count":25,"area":"alignment"},{"id":"2506.10949","title":"Monitoring Decomposition Attacks in LLMs with Lightweight Sequential Monitors","created":"2025-06-12","cited_by_count":25,"area":"safety"},{"id":"2408.04811","title":"h4rm3l: A language for Composable Jailbreak Attack Synthesis","created":"2024-08-09","cited_by_count":24,"area":"safety"},{"id":"2406.06369","title":"Annotation alignment: Comparing LLM and human annotations of conversational safety","created":"2024-06-10","cited_by_count":23,"area":null},{"id":"2407.08770","title":"Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing","created":"2024-07-11","cited_by_count":23,"area":"alignment"},{"id":"2507.00971","title":"Reasoning as an Adaptive Defense for Safety","created":"2025-07-01","cited_by_count":23,"area":"lr"},{"id":"2507.01915","title":"Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models","created":"2025-07-02","cited_by_count":23,"area":"alignment"},{"id":"2407.07342","title":"Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture","created":"2024-07-10","cited_by_count":22,"area":"alignment"},{"id":"2410.10343","title":"Locking Down the Finetuned LLMs Safety","created":"2024-10-14","cited_by_count":22,"area":null},{"id":"2502.20968","title":"Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs","created":"2025-02-28","cited_by_count":22,"area":null},{"id":"2505.06843","title":"Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety","created":"2025-05-11","cited_by_count":22,"area":"safety"},{"id":"2411.08410","title":"The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense","created":"2024-11-13","cited_by_count":21,"area":"safety"},{"id":"2311.02105","title":"Making Harmful Behaviors Unlearnable for Large Language Models","created":"2023-11-02","cited_by_count":20,"area":null},{"id":"2401.10647","title":"Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models","created":"2024-01-19","cited_by_count":20,"area":"safety"},{"id":"2404.07900","title":"High-Dimension Human Value Representation in Large Language Models","created":"2024-04-11","cited_by_count":20,"area":null},{"id":"2501.14940","title":"CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models","created":"2025-01-24","cited_by_count":20,"area":"alignment"},{"id":"2501.18100","title":"Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation","created":"2025-01-30","cited_by_count":20,"area":null}],"next_cursor":"100"}