{"total":505,"rows":[{"id":"2412.16720","title":"OpenAI o1 System Card","created":"2024-12-21","cited_by_count":1244,"area":"lr"},{"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":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053,"area":"lr"},{"id":"2309.10253","title":"GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts","created":"2023-09-19","cited_by_count":560,"area":"safety"},{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536,"area":"safety"},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499,"area":"alignment"},{"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":"2309.11998","title":"LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset","created":"2023-09-21","cited_by_count":461,"area":null},{"id":"2309.07875","title":"Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions","created":"2023-09-14","cited_by_count":387,"area":null},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322,"area":"safety"},{"id":"2410.12784","title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","created":"2024-10-16","cited_by_count":318,"area":null},{"id":"2412.16339","title":"Deliberative Alignment: Reasoning Enables Safer Language Models","created":"2024-12-20","cited_by_count":308,"area":"lr"},{"id":"2506.04178","title":"OpenThoughts: Data Recipes for Reasoning Models","created":"2025-06-04","cited_by_count":304,"area":"lr"},{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"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":"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":"2507.01352","title":"Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy","created":"2025-07-02","cited_by_count":214,"area":"lr"},{"id":"2309.14348","title":"Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM","created":"2023-09-18","cited_by_count":192,"area":"alignment"},{"id":"2410.16184","title":"RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style","created":"2024-10-21","cited_by_count":176,"area":"alignment"},{"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":"2510.14276","title":"Qwen3Guard Technical Report","created":"2025-10-16","cited_by_count":155,"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":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128,"area":null},{"id":"2507.18624","title":"Checklists Are Better Than Reward Models For Aligning Language Models","created":"2025-07-24","cited_by_count":128,"area":"alignment"},{"id":"2504.13203","title":"X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents","created":"2025-04-15","cited_by_count":125,"area":"agents"},{"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":"2502.17420","title":"The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence","created":"2025-02-24","cited_by_count":115,"area":"alignment"},{"id":"2309.12342","title":"Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions","created":"2023-08-25","cited_by_count":112,"area":null},{"id":"2411.01111","title":"Rule Based Rewards for Language Model Safety","created":"2024-11-02","cited_by_count":108,"area":"alignment"},{"id":"2401.17256","title":"Weak-to-Strong Jailbreaking on Large Language Models","created":"2024-01-30","cited_by_count":107,"area":"safety"},{"id":"2311.11855","title":"Evil Geniuses: Delving into the Safety of LLM-based Agents","created":"2023-11-20","cited_by_count":106,"area":"agents"},{"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":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100,"area":"lr"},{"id":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96,"area":"safety"},{"id":"2411.11296","title":"Steering Language Model Refusal with Sparse Autoencoders","created":"2024-11-18","cited_by_count":95,"area":"mechinterp"},{"id":"2507.11878","title":"LLMs Encode Harmfulness and Refusal Separately","created":"2025-07-16","cited_by_count":88,"area":"safety"},{"id":"2401.15897","title":"Red-Teaming for Generative AI: Silver Bullet or Security Theater?","created":"2024-01-29","cited_by_count":83,"area":"safety"},{"id":"2308.12833","title":"Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities","created":"2023-08-24","cited_by_count":82,"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":"2502.02384","title":"STAIR: Improving Safety Alignment with Introspective Reasoning","created":"2025-02-04","cited_by_count":77,"area":"lr"},{"id":"2311.08370","title":"SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models","created":"2023-11-14","cited_by_count":76,"area":null},{"id":"2402.00357","title":"Safety of Multimodal Large Language Models on Images and Texts","created":"2024-02-01","cited_by_count":75,"area":"mllm"},{"id":"2407.17436","title":"AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies","created":"2024-07-11","cited_by_count":74,"area":null},{"id":"2510.07192","title":"Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples","created":"2025-10-08","cited_by_count":72,"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":"2402.01822","title":"Building Guardrails for Large Language Models","created":"2024-02-02","cited_by_count":65,"area":"safety"},{"id":"2503.24370","title":"Effectively Controlling Reasoning Models through Thinking Intervention","created":"2025-03-31","cited_by_count":65,"area":"lr"},{"id":"2409.20089","title":"Robust LLM safeguarding via refusal feature adversarial training","created":"2024-09-30","cited_by_count":64,"area":null},{"id":"2504.10081","title":"RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability","created":"2025-04-14","cited_by_count":59,"area":"lr"},{"id":"2412.07097","title":"On Evaluating the Durability of Safeguards for Open-Weight LLMs","created":"2024-12-10","cited_by_count":52,"area":null},{"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":"2603.20633","title":"Seed1.8 Model Card: Towards Generalized Real-World Agency","created":"2026-03-21","cited_by_count":50,"area":null},{"id":"2506.07022","title":"AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint","created":"2025-06-08","cited_by_count":49,"area":"safety"},{"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":"2411.16721","title":"Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks","created":"2024-11-23","cited_by_count":48,"area":"mllm"},{"id":"2310.02224","title":"Can Language Models be Instructed to Protect Personal Information?","created":"2023-10-03","cited_by_count":46,"area":"mllm"},{"id":"2405.20850","title":"Improving Reward Models with Synthetic Critiques","created":"2024-05-31","cited_by_count":44,"area":"alignment"},{"id":"2407.08351","title":"AutoBencher: Towards Declarative Benchmark Construction","created":"2024-07-11","cited_by_count":44,"area":null},{"id":"2407.05557","title":"$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning","created":"2024-07-08","cited_by_count":43,"area":"lr"},{"id":"2409.20370","title":"The Perfect Blend: Redefining RLHF with Mixture of Judges","created":"2024-09-30","cited_by_count":43,"area":"alignment"},{"id":"2503.03710","title":"Improving LLM Safety Alignment with Dual-Objective Optimization","created":"2025-03-05","cited_by_count":43,"area":"alignment"},{"id":"2505.11049","title":"GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning","created":"2025-05-16","cited_by_count":42,"area":"lr"},{"id":"2501.12895","title":"Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback","created":"2025-01-22","cited_by_count":41,"area":"alignment"},{"id":"2503.05021","title":"Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety","created":"2025-03-06","cited_by_count":39,"area":"lr"},{"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":"2508.18076","title":"Neither Valid nor Reliable? Investigating the Use of LLMs as Judges","created":"2025-08-25","cited_by_count":39,"area":null},{"id":"2505.20065","title":"SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety","created":"2025-05-26","cited_by_count":37,"area":"alignment"},{"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":"2409.15268","title":"Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking","created":"2024-09-23","cited_by_count":35,"area":"alignment"},{"id":"2502.14744","title":"HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States","created":"2025-02-20","cited_by_count":33,"area":"mllm"},{"id":"2505.10833","title":"MergeBench: A Benchmark for Merging Domain-Specialized LLMs","created":"2025-05-16","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":"2406.09321","title":"JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models","created":"2024-06-13","cited_by_count":31,"area":"safety"},{"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":"2510.09781","title":"Building a Foundational Guardrail for General Agentic Systems via Synthetic Data","created":"2025-10-10","cited_by_count":29,"area":"agents"},{"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":"2405.13581","title":"Safety Alignment for Vision Language Models","created":"2024-05-22","cited_by_count":28,"area":"mllm"},{"id":"2506.03637","title":"RewardAnything: Generalizable Principle-Following Reward Models","created":"2025-06-04","cited_by_count":28,"area":"alignment"},{"id":"2507.06187","title":"The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains","created":"2025-07-08","cited_by_count":28,"area":null},{"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":"2410.02197","title":"Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment","created":"2024-10-03","cited_by_count":27,"area":"alignment"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2504.09420","title":"SaRO: Enhancing LLM Safety through Reasoning-based Alignment","created":"2025-04-13","cited_by_count":26,"area":"lr"},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2310.14303","title":"Language Model Unalignment: Parametric Red-Teaming to Expose Hidden Harms and Biases","created":"2023-10-22","cited_by_count":24,"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":"2505.14667","title":"SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment","created":"2025-05-20","cited_by_count":24,"area":"lr"},{"id":"2506.14922","title":"FORTRESS: Frontier Risk Evaluation for National Security and Public Safety","created":"2025-06-17","cited_by_count":24,"area":"safety"},{"id":"2507.04250","title":"Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning","created":"2025-07-06","cited_by_count":24,"area":"alignment"},{"id":"2402.09193","title":"(Ir)rationality and Cognitive Biases in Large Language Models","created":"2024-02-14","cited_by_count":23,"area":"lr"},{"id":"2410.10414","title":"On Calibration of LLM-based Guard Models for Reliable Content Moderation","created":"2024-10-14","cited_by_count":23,"area":"safety"},{"id":"2507.00971","title":"Reasoning as an Adaptive Defense for Safety","created":"2025-07-01","cited_by_count":23,"area":"lr"},{"id":"2503.05139","title":"Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs","created":"2025-03-07","cited_by_count":22,"area":"moe"},{"id":"2503.06550","title":"BingoGuard: LLM Content Moderation Tools with Risk Levels","created":"2025-03-09","cited_by_count":21,"area":null},{"id":"2602.01539","title":"MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety","created":"2026-02-02","cited_by_count":21,"area":"alignment"},{"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":"2502.09990","title":"X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability","created":"2025-02-14","cited_by_count":20,"area":"alignment"}],"next_cursor":"100"}