{"total":246,"rows":[{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065,"area":"lr"},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982,"area":"lr"},{"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":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686,"area":"lr"},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672,"area":"lr"},{"id":"2405.01470","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","created":"2024-05-02","cited_by_count":629,"area":null},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499,"area":"alignment"},{"id":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463,"area":"alignment"},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403,"area":"lr"},{"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":"2310.06452","title":"Understanding the Effects of RLHF on LLM Generalisation and Diversity","created":"2023-10-10","cited_by_count":396,"area":"alignment"},{"id":"2309.06657","title":"Statistical Rejection Sampling Improves Preference Optimization","created":"2023-09-13","cited_by_count":323,"area":"alignment"},{"id":"2501.09686","title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","created":"2025-01-16","cited_by_count":293,"area":"wm"},{"id":"2310.03716","title":"A Long Way to Go: Investigating Length Correlations in RLHF","created":"2023-10-05","cited_by_count":291,"area":"alignment"},{"id":"2404.10719","title":"Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study","created":"2024-04-16","cited_by_count":262,"area":"alignment"},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"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":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228,"area":"agents"},{"id":"2303.04226","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","created":"2023-03-07","cited_by_count":224,"area":null},{"id":"2311.08401","title":"Fine-tuning Language Models for Factuality","created":"2023-11-14","cited_by_count":221,"area":null},{"id":"2305.14283","title":"Query Rewriting for Retrieval-Augmented Large Language Models","created":"2023-05-23","cited_by_count":213,"area":"rag"},{"id":"2304.01904","title":"REFINER: Reasoning Feedback on Intermediate Representations","created":"2023-04-04","cited_by_count":205,"area":"lr"},{"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":"2506.23918","title":"Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers","created":"2025-06-30","cited_by_count":199,"area":"lr"},{"id":"2302.02662","title":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning","created":"2023-02-06","cited_by_count":195,"area":null},{"id":"2212.08061","title":"On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning","created":"2022-12-15","cited_by_count":194,"area":"lr"},{"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":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183,"area":"alignment"},{"id":"2311.01460","title":"Implicit Chain of Thought Reasoning via Knowledge Distillation","created":"2023-11-02","cited_by_count":176,"area":"lr"},{"id":"2403.04642","title":"Teaching Large Language Models to Reason with Reinforcement Learning","created":"2024-03-07","cited_by_count":160,"area":"lr"},{"id":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158,"area":"lr"},{"id":"2502.05450","title":"ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy","created":"2025-02-08","cited_by_count":154,"area":"vla"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2404.12253","title":"Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing","created":"2024-04-18","cited_by_count":125,"area":"lr"},{"id":"2310.03708","title":"Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization","created":"2023-10-05","cited_by_count":124,"area":"alignment"},{"id":"2402.12348","title":"GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations","created":"2024-02-19","cited_by_count":120,"area":"lr"},{"id":"2308.03549","title":"Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-world Multi-turn Dialogue","created":"2023-08-07","cited_by_count":119,"area":"alignment"},{"id":"2501.16664","title":"Improving Vision-Language-Action Model with Online Reinforcement Learning","created":"2025-01-28","cited_by_count":116,"area":"mllm"},{"id":"2505.19789","title":"What Can RL Bring to VLA Generalization? An Empirical Study","created":"2025-05-26","cited_by_count":108,"area":"vla"},{"id":"2305.08844","title":"RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs","created":"2023-05-15","cited_by_count":105,"area":null},{"id":"2404.04465","title":"Aligning Diffusion Models by Optimizing Human Utility","created":"2024-04-06","cited_by_count":101,"area":"diffusion"},{"id":"2309.00779","title":"Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties","created":"2023-09-02","cited_by_count":97,"area":null},{"id":"2310.04373","title":"Confronting Reward Model Overoptimization with Constrained RLHF","created":"2023-10-06","cited_by_count":96,"area":"alignment"},{"id":"2302.11520","title":"Guiding Large Language Models via Directional Stimulus Prompting","created":"2023-02-22","cited_by_count":95,"area":null},{"id":"2305.11391","title":"A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation","created":"2023-05-19","cited_by_count":93,"area":null},{"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":"2311.18232","title":"LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models","created":"2023-11-30","cited_by_count":88,"area":null},{"id":"2404.10642","title":"Self-playing Adversarial Language Game Enhances LLM Reasoning","created":"2024-04-16","cited_by_count":83,"area":"lr"},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"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":"2403.08730","title":"Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization","created":"2024-03-13","cited_by_count":75,"area":"mllm"},{"id":"2312.15997","title":"Aligning Large Language Models with Human Preferences through Representation Engineering","created":"2023-12-26","cited_by_count":71,"area":"alignment"},{"id":"2404.16767","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","created":"2024-04-25","cited_by_count":69,"area":"alignment"},{"id":"2402.02992","title":"Decoding-time Realignment of Language Models","created":"2024-02-05","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":"2310.00212","title":"Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment","created":"2023-09-30","cited_by_count":57,"area":"alignment"},{"id":"2401.16335","title":"Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF","created":"2024-01-29","cited_by_count":57,"area":"alignment"},{"id":"2401.00243","title":"Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles","created":"2023-12-30","cited_by_count":56,"area":"alignment"},{"id":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55,"area":null},{"id":"2402.08265","title":"A Dense Reward View on Aligning Text-to-Image Diffusion with Preference","created":"2024-02-13","cited_by_count":55,"area":"diffusion"},{"id":"2408.13890","title":"Making Large Language Models Better Planners with Reasoning-Decision Alignment","created":"2024-08-25","cited_by_count":52,"area":"lr"},{"id":"2311.10766","title":"Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values","created":"2023-11-15","cited_by_count":50,"area":null},{"id":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49,"area":null},{"id":"2405.06639","title":"Value Augmented Sampling for Language Model Alignment and Personalization","created":"2024-05-10","cited_by_count":49,"area":"alignment"},{"id":"2405.14431","title":"RaFe: Ranking Feedback Improves Query Rewriting for RAG","created":"2024-05-23","cited_by_count":49,"area":"rag"},{"id":"2505.11711","title":"Reinforcement Learning Finetunes Small Subnetworks in Large Language Models","created":"2025-05-16","cited_by_count":49,"area":null},{"id":"2306.02231","title":"Fine-Tuning Language Models with Advantage-Induced Policy Alignment","created":"2023-06-04","cited_by_count":48,"area":"alignment"},{"id":"2405.19534","title":"Preference Learning Algorithms Do Not Learn Preference Rankings","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2406.08705","title":"When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search","created":"2024-06-13","cited_by_count":47,"area":"safety"},{"id":"2212.10938","title":"Critic-Guided Decoding for Controlled Text Generation","created":"2022-12-21","cited_by_count":45,"area":null},{"id":"2308.12014","title":"From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models","created":"2023-08-23","cited_by_count":45,"area":"alignment"},{"id":"2404.17287","title":"When to Trust LLMs: Aligning Confidence with Response Quality","created":"2024-04-26","cited_by_count":43,"area":null},{"id":"2407.16574","title":"TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback","created":"2024-07-23","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":"2404.08495","title":"Dataset Reset Policy Optimization for RLHF","created":"2024-04-12","cited_by_count":41,"area":"alignment"},{"id":"2406.05534","title":"Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing","created":"2024-06-08","cited_by_count":39,"area":"alignment"},{"id":"2311.05584","title":"Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations","created":"2023-11-09","cited_by_count":38,"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":"2212.10409","title":"ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations","created":"2022-12-20","cited_by_count":36,"area":null},{"id":"2301.12842","title":"Direct Preference-based Policy Optimization without Reward Modeling","created":"2023-01-30","cited_by_count":36,"area":"alignment"},{"id":"2402.10958","title":"Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts","created":"2024-02-12","cited_by_count":36,"area":"alignment"},{"id":"2311.04072","title":"Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment","created":"2023-11-07","cited_by_count":35,"area":"alignment"},{"id":"2407.00782","title":"Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning","created":"2024-06-30","cited_by_count":35,"area":"lr"},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2312.07551","title":"Language Model Alignment with Elastic Reset","created":"2023-12-06","cited_by_count":34,"area":"alignment"},{"id":"2401.05033","title":"Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk","created":"2024-01-10","cited_by_count":34,"area":"agents"},{"id":"2406.19371","title":"Suri: Multi-constraint Instruction Following for Long-form Text Generation","created":"2024-06-27","cited_by_count":34,"area":"alignment"},{"id":"2506.23235","title":"Generalist Reward Models: Found Inside Large Language Models","created":"2025-06-29","cited_by_count":34,"area":"alignment"},{"id":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2405.17888","title":"Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment","created":"2024-05-28","cited_by_count":32,"area":"alignment"},{"id":"2306.00398","title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning","created":"2023-06-01","cited_by_count":31,"area":"alignment"},{"id":"2406.10957","title":"Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence","created":"2024-06-16","cited_by_count":31,"area":"alignment"},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30,"area":"alignment"},{"id":"2503.04550","title":"Benchmarking Reasoning Robustness in Large Language Models","created":"2025-03-06","cited_by_count":30,"area":"lr"},{"id":"2306.06941","title":"The BEA 2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues","created":"2023-06-12","cited_by_count":27,"area":null},{"id":"2310.11958","title":"Emptying the Ocean with a Spoon: Should We Edit Models?","created":"2023-10-18","cited_by_count":27,"area":null},{"id":"2310.20703","title":"Vanishing Gradients in Reinforcement Finetuning of Language Models","created":"2023-10-31","cited_by_count":27,"area":null},{"id":"2403.01857","title":"Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences","created":"2024-03-04","cited_by_count":27,"area":"alignment"}],"next_cursor":"100"}