{"total":626,"rows":[{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104,"area":"alignment"},{"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":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100,"area":"alignment"},{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860,"area":"alignment"},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812,"area":"alignment"},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748,"area":"alignment"},{"id":"2404.13076","title":"LLM Evaluators Recognize and Favor Their Own Generations","created":"2024-04-15","cited_by_count":686,"area":"alignment"},{"id":"2401.10020","title":"Self-Rewarding Language Models","created":"2024-01-18","cited_by_count":681,"area":"alignment"},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651,"area":"alignment"},{"id":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625,"area":"alignment"},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499,"area":"alignment"},{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472,"area":"alignment"},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2310.06387","title":"Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations","created":"2023-10-10","cited_by_count":431,"area":"alignment"},{"id":"2308.06463","title":"GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher","created":"2023-08-12","cited_by_count":423,"area":"alignment"},{"id":"2302.12192","title":"Aligning Text-to-Image Models using Human Feedback","created":"2023-02-23","cited_by_count":422,"area":"alignment"},{"id":"2310.01377","title":"UltraFeedback: Boosting Language Models with Scaled AI Feedback","created":"2023-10-02","cited_by_count":406,"area":"alignment"},{"id":"2305.10425","title":"SLiC-HF: Sequence Likelihood Calibration with Human Feedback","created":"2023-05-17","cited_by_count":401,"area":"alignment"},{"id":"2306.01693","title":"Fine-Grained Human Feedback Gives Better Rewards for Language Model Training","created":"2023-06-02","cited_by_count":401,"area":"alignment"},{"id":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360,"area":"alignment"},{"id":"2312.11456","title":"Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint","created":"2023-12-18","cited_by_count":350,"area":"alignment"},{"id":"2305.03047","title":"Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision","created":"2023-05-04","cited_by_count":318,"area":"alignment"},{"id":"2306.17492","title":"Preference Ranking Optimization for Human Alignment","created":"2023-06-30","cited_by_count":285,"area":"alignment"},{"id":"2402.06782","title":"Debating with More Persuasive LLMs Leads to More Truthful Answers","created":"2024-02-09","cited_by_count":266,"area":"alignment"},{"id":"2312.14925","title":"A Survey of Reinforcement Learning from Human Feedback","created":"2023-12-22","cited_by_count":264,"area":"alignment"},{"id":"2402.04792","title":"Direct Language Model Alignment from Online AI Feedback","created":"2024-02-07","cited_by_count":260,"area":"alignment"},{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247,"area":"alignment"},{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"area":"alignment"},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2310.02743","title":"Reward Model Ensembles Help Mitigate Overoptimization","created":"2023-10-04","cited_by_count":231,"area":"alignment"},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"id":"2307.04964","title":"Secrets of RLHF in Large Language Models Part I: PPO","created":"2023-07-11","cited_by_count":229,"area":"alignment"},{"id":"2305.15075","title":"HuatuoGPT, towards Taming Language Model to Be a Doctor","created":"2023-05-24","cited_by_count":214,"area":"alignment"},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201,"area":"alignment"},{"id":"2310.20624","title":"LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B","created":"2023-10-31","cited_by_count":195,"area":"alignment"},{"id":"2309.14348","title":"Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM","created":"2023-09-18","cited_by_count":192,"area":"alignment"},{"id":"2310.10505","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","created":"2023-10-16","cited_by_count":187,"area":"alignment"},{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184,"area":"alignment"},{"id":"2404.03715","title":"Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences","created":"2024-04-04","cited_by_count":178,"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":"2309.16240","title":"Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints","created":"2023-09-28","cited_by_count":174,"area":"alignment"},{"id":"2309.07124","title":"RAIN: Your Language Models Can Align Themselves without Finetuning","created":"2023-09-13","cited_by_count":157,"area":"alignment"},{"id":"2408.10075","title":"Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning","created":"2024-08-19","cited_by_count":155,"area":"alignment"},{"id":"2302.02676","title":"Chain of Hindsight Aligns Language Models with Feedback","created":"2023-02-06","cited_by_count":148,"area":"alignment"},{"id":"2402.18571","title":"Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards","created":"2024-02-28","cited_by_count":148,"area":"alignment"},{"id":"2410.12832","title":"Generative Reward Models","created":"2024-10-02","cited_by_count":148,"area":"alignment"},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144,"area":"alignment"},{"id":"2404.16019","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","created":"2024-04-24","cited_by_count":144,"area":"alignment"},{"id":"2402.07319","title":"ODIN: Disentangled Reward Mitigates Hacking in RLHF","created":"2024-02-11","cited_by_count":136,"area":"alignment"},{"id":"2511.18397","title":"Natural Emergent Misalignment from Reward Hacking in Production RL","created":"2025-11-23","cited_by_count":136,"area":"alignment"},{"id":"2312.08358","title":"Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF","created":"2023-12-13","cited_by_count":133,"area":"alignment"},{"id":"2303.16755","title":"Training Language Models with Language Feedback at Scale","created":"2023-03-28","cited_by_count":128,"area":"alignment"},{"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":"2406.07814","title":"Collective Constitutional AI: Aligning a Language Model with Public Input","created":"2024-06-12","cited_by_count":123,"area":"alignment"},{"id":"2311.04155","title":"Black-Box Prompt Optimization: Aligning Large Language Models without Model Training","created":"2023-11-07","cited_by_count":122,"area":"alignment"},{"id":"2406.15951","title":"Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration","created":"2024-06-22","cited_by_count":113,"area":"alignment"},{"id":"2405.08448","title":"Understanding the performance gap between online and offline alignment algorithms","created":"2024-05-14","cited_by_count":110,"area":"alignment"},{"id":"2402.14740","title":"Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs","created":"2024-02-22","cited_by_count":108,"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":"2408.11791","title":"Critique-out-Loud Reward Models","created":"2024-08-21","cited_by_count":106,"area":"alignment"},{"id":"2402.16914","title":"DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers","created":"2024-02-25","cited_by_count":101,"area":"alignment"},{"id":"2404.10271","title":"Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback","created":"2024-04-16","cited_by_count":100,"area":"alignment"},{"id":"2402.02416","title":"Aligner: Efficient Alignment by Learning to Correct","created":"2024-02-04","cited_by_count":98,"area":"alignment"},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"area":"alignment"},{"id":"2401.13136","title":"The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts","created":"2024-01-23","cited_by_count":94,"area":"alignment"},{"id":"2310.10076","title":"Verbosity Bias in Preference Labeling by Large Language Models","created":"2023-10-16","cited_by_count":91,"area":"alignment"},{"id":"2403.08635","title":"Human Alignment of Large Language Models through Online Preference Optimisation","created":"2024-03-13","cited_by_count":91,"area":"alignment"},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2410.14872","title":"How to Evaluate Reward Models for RLHF","created":"2024-10-18","cited_by_count":88,"area":"alignment"},{"id":"2303.05453","title":"Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback","created":"2023-03-09","cited_by_count":87,"area":"alignment"},{"id":"2402.04833","title":"Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning","created":"2024-02-07","cited_by_count":85,"area":"alignment"},{"id":"2405.17977","title":"Aligning to Thousands of Preferences via System Message Generalization","created":"2024-05-28","cited_by_count":84,"area":"alignment"},{"id":"2402.02030","title":"Panacea: Pareto Alignment via Preference Adaptation for LLMs","created":"2024-02-03","cited_by_count":80,"area":"alignment"},{"id":"2305.16960","title":"Training Socially Aligned Language Models on Simulated Social Interactions","created":"2023-05-26","cited_by_count":78,"area":"alignment"},{"id":"2310.05199","title":"Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback","created":"2023-10-08","cited_by_count":78,"area":"alignment"},{"id":"2402.00782","title":"Dense Reward for Free in Reinforcement Learning from Human Feedback","created":"2024-02-01","cited_by_count":78,"area":"alignment"},{"id":"2402.06627","title":"Feedback Loops With Language Models Drive In-Context Reward Hacking","created":"2024-02-09","cited_by_count":77,"area":"alignment"},{"id":"2409.13156","title":"RRM: Robust Reward Model Training Mitigates Reward Hacking","created":"2024-09-20","cited_by_count":76,"area":"alignment"},{"id":"2305.13735","title":"Aligning Large Language Models through Synthetic Feedback","created":"2023-05-23","cited_by_count":75,"area":"alignment"},{"id":"2312.07000","title":"Alignment for Honesty","created":"2023-12-12","cited_by_count":74,"area":"alignment"},{"id":"2410.18252","title":"Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models","created":"2024-10-23","cited_by_count":70,"area":"alignment"},{"id":"2311.18743","title":"AlignBench: Benchmarking Chinese Alignment of Large Language Models","created":"2023-11-30","cited_by_count":68,"area":"alignment"},{"id":"2405.14655","title":"Multi-turn Reinforcement Learning from Preference Human Feedback","created":"2024-05-23","cited_by_count":67,"area":"alignment"},{"id":"2410.08847","title":"Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization","created":"2024-10-11","cited_by_count":67,"area":"alignment"},{"id":"2310.11523","title":"Group Preference Optimization: Few-Shot Alignment of Large Language Models","created":"2023-10-17","cited_by_count":63,"area":"alignment"},{"id":"2410.03642","title":"Aligning LLMs with Individual Preferences via Interaction","created":"2024-10-04","cited_by_count":63,"area":"alignment"},{"id":"2507.08794","title":"One Token to Fool LLM-as-a-Judge","created":"2025-07-11","cited_by_count":60,"area":"alignment"},{"id":"2402.08114","title":"Active Preference Learning for Large Language Models","created":"2024-02-12","cited_by_count":58,"area":"alignment"},{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"area":"alignment"},{"id":"2310.00212","title":"Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment","created":"2023-09-30","cited_by_count":57,"area":"alignment"},{"id":"2403.09032","title":"CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences","created":"2024-03-14","cited_by_count":57,"area":"alignment"},{"id":"2310.05910","title":"SALMON: Self-Alignment with Instructable Reward Models","created":"2023-10-09","cited_by_count":55,"area":"alignment"},{"id":"2402.06147","title":"DeAL: Decoding-time Alignment for Large Language Models","created":"2024-02-05","cited_by_count":55,"area":"alignment"},{"id":"2406.08469","title":"PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences","created":"2024-06-12","cited_by_count":54,"area":"alignment"},{"id":"2402.07314","title":"Online Iterative Reinforcement Learning from Human Feedback with General Preference Model","created":"2024-02-11","cited_by_count":52,"area":"alignment"},{"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":"2410.15522","title":"M-RewardBench: Evaluating Reward Models in Multilingual Settings","created":"2024-10-20","cited_by_count":50,"area":"alignment"}],"next_cursor":"100"}