{"total":625,"rows":[{"id":"2311.12908","title":"Diffusion Model Alignment Using Direct Preference Optimization","created":"2023-11-21","cited_by_count":790,"area":"wm"},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557,"area":"synth"},{"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":"2406.03816","title":"ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search","created":"2024-06-06","cited_by_count":344,"area":"lr"},{"id":"2309.06657","title":"Statistical Rejection Sampling Improves Preference Optimization","created":"2023-09-13","cited_by_count":323,"area":"alignment"},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2310.07641","title":"Evaluating Large Language Models at Evaluating Instruction Following","created":"2023-10-11","cited_by_count":302,"area":null},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"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":"2401.05459","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","created":"2024-01-10","cited_by_count":260,"area":"agents"},{"id":"2402.04792","title":"Direct Language Model Alignment from Online AI Feedback","created":"2024-02-07","cited_by_count":260,"area":"alignment"},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2405.00451","title":"Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning","created":"2024-05-01","cited_by_count":241,"area":"lr"},{"id":"2312.00886","title":"Nash Learning from Human Feedback","created":"2023-12-01","cited_by_count":224,"area":"alignment"},{"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":"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":"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":"2506.01347","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","created":"2025-06-02","cited_by_count":162,"area":"lr"},{"id":"2309.07124","title":"RAIN: Your Language Models Can Align Themselves without Finetuning","created":"2023-09-13","cited_by_count":157,"area":"alignment"},{"id":"2411.00816","title":"CycleResearcher: Improving Automated Research via Automated Review","created":"2024-10-28","cited_by_count":148,"area":null},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2511.00088","title":"Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail","created":"2025-10-30","cited_by_count":146,"area":"lr"},{"id":"2402.07319","title":"ODIN: Disentangled Reward Mitigates Hacking in RLHF","created":"2024-02-11","cited_by_count":136,"area":"alignment"},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2312.10665","title":"Silkie: Preference Distillation for Large Visual Language Models","created":"2023-12-17","cited_by_count":130,"area":"mllm"},{"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":"2502.01534","title":"Preference Leakage: A Contamination Problem in LLM-as-a-judge","created":"2025-02-03","cited_by_count":125,"area":null},{"id":"2502.00640","title":"CollabLLM: From Passive Responders to Active Collaborators","created":"2025-02-02","cited_by_count":124,"area":null},{"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":"2309.16289","title":"LawBench: Benchmarking Legal Knowledge of Large Language Models","created":"2023-09-28","cited_by_count":117,"area":null},{"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":"2408.11791","title":"Critique-out-Loud Reward Models","created":"2024-08-21","cited_by_count":106,"area":"alignment"},{"id":"2311.07362","title":"Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision","created":"2023-11-13","cited_by_count":98,"area":"mllm"},{"id":"2402.02416","title":"Aligner: Efficient Alignment by Learning to Correct","created":"2024-02-04","cited_by_count":98,"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":"2407.03502","title":"AgentInstruct: Toward Generative Teaching with Agentic Flows","created":"2024-07-03","cited_by_count":89,"area":"agents"},{"id":"2402.12840","title":"ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic","created":"2024-02-20","cited_by_count":88,"area":"lr"},{"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":"2406.12030","title":"SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model","created":"2024-06-17","cited_by_count":85,"area":"mllm"},{"id":"2506.10943","title":"Self-Adapting Language Models","created":"2025-06-12","cited_by_count":84,"area":null},{"id":"2312.01823","title":"Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication","created":"2023-12-04","cited_by_count":82,"area":"lr"},{"id":"2508.17536","title":"Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?","created":"2025-08-24","cited_by_count":81,"area":"lr"},{"id":"2402.02030","title":"Panacea: Pareto Alignment via Preference Adaptation for LLMs","created":"2024-02-03","cited_by_count":80,"area":"alignment"},{"id":"2404.14233","title":"Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback","created":"2024-04-22","cited_by_count":80,"area":"mllm"},{"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":"2501.18099","title":"Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge","created":"2025-01-30","cited_by_count":78,"area":"lr"},{"id":"2309.12053","title":"AceGPT, Localizing Large Language Models in Arabic","created":"2023-09-21","cited_by_count":75,"area":"alignment"},{"id":"2401.06561","title":"Intention Analysis Makes LLMs A Good Jailbreak Defender","created":"2024-01-12","cited_by_count":74,"area":"alignment"},{"id":"2405.15973","title":"Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement","created":"2024-05-24","cited_by_count":74,"area":"lr"},{"id":"2408.02666","title":"Self-Taught Evaluators","created":"2024-08-05","cited_by_count":72,"area":"alignment"},{"id":"2506.09033","title":"Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning","created":"2025-06-10","cited_by_count":72,"area":null},{"id":"2411.16646","title":"Self-Generated Critiques Boost Reward Modeling for Language Models","created":"2024-11-25","cited_by_count":71,"area":"lr"},{"id":"2402.17262","title":"Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue","created":"2024-02-27","cited_by_count":66,"area":"safety"},{"id":"2505.23646","title":"Are Reasoning Models More Prone to Hallucination?","created":"2025-05-29","cited_by_count":64,"area":"lr"},{"id":"2602.05125","title":"Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks","created":"2026-02-04","cited_by_count":62,"area":"lr"},{"id":"2507.08794","title":"One Token to Fool LLM-as-a-Judge","created":"2025-07-11","cited_by_count":60,"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":"2402.10110","title":"Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning","created":"2024-02-15","cited_by_count":57,"area":null},{"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":"2404.09656","title":"Learn Your Reference Model for Real Good Alignment","created":"2024-04-15","cited_by_count":57,"area":"alignment"},{"id":"2402.18191","title":"Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation","created":"2024-02-28","cited_by_count":53,"area":null},{"id":"2406.09760","title":"Bootstrapping Language Models with DPO Implicit Rewards","created":"2024-06-14","cited_by_count":53,"area":"alignment"},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"area":"alignment"},{"id":"2401.04536","title":"Evaluating Language Model Agency through Negotiations","created":"2024-01-09","cited_by_count":48,"area":null},{"id":"2402.10038","title":"RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Models","created":"2024-02-15","cited_by_count":48,"area":"alignment"},{"id":"2405.19107","title":"Offline Regularised Reinforcement Learning for Large Language Models Alignment","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2411.04991","title":"Rethinking Bradley-Terry Models in Preference-Based Reward Modeling: Foundations, Theory, and Alternatives","created":"2024-11-07","cited_by_count":48,"area":"lr"},{"id":"2501.19054","title":"Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models","created":"2025-01-31","cited_by_count":47,"area":null},{"id":"2507.05386","title":"Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training","created":"2025-07-07","cited_by_count":47,"area":null},{"id":"2402.05699","title":"Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation","created":"2024-02-08","cited_by_count":46,"area":"alignment"},{"id":"2402.01117","title":"DTS-SQL: Decomposed Text-to-SQL with Small Large Language Models","created":"2024-02-02","cited_by_count":45,"area":null},{"id":"2506.22316","title":"Evaluating Scoring Bias in LLM-as-a-Judge","created":"2025-06-27","cited_by_count":43,"area":null},{"id":"2510.04340","title":"Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time","created":"2025-10-05","cited_by_count":43,"area":null},{"id":"2310.13595","title":"The History and Risks of Reinforcement Learning and Human Feedback","created":"2023-10-20","cited_by_count":42,"area":"alignment"},{"id":"2404.09824","title":"Impact of Preference Noise on the Alignment Performance of Generative Language Models","created":"2024-04-15","cited_by_count":41,"area":"alignment"},{"id":"2310.13032","title":"Quality-Diversity through AI Feedback","created":"2023-10-19","cited_by_count":40,"area":null},{"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":"2509.17940","title":"DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving","created":"2025-09-22","cited_by_count":39,"area":"driving"},{"id":"2504.03846","title":"Do LLM Evaluators Prefer Themselves for a Reason?","created":"2025-04-04","cited_by_count":38,"area":"lr"},{"id":"2503.03064","title":"Improving LLM-as-a-Judge Inference with the Judgment Distribution","created":"2025-03-04","cited_by_count":37,"area":null},{"id":"2402.03659","title":"Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models","created":"2024-02-06","cited_by_count":36,"area":null},{"id":"2402.03746","title":"Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback","created":"2024-02-06","cited_by_count":36,"area":"mllm"},{"id":"2309.13339","title":"Enhancing Zero-Shot Chain-of-Thought Reasoning in Large Language Models through Logic","created":"2023-09-23","cited_by_count":35,"area":"lr"},{"id":"2310.10477","title":"Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis","created":"2023-10-16","cited_by_count":35,"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":"2404.05530","title":"Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data","created":"2024-04-08","cited_by_count":35,"area":"alignment"},{"id":"2409.07253","title":"Alignment of Diffusion Models: Fundamentals, Challenges, and Future","created":"2024-09-11","cited_by_count":35,"area":"diffusion"},{"id":"2402.10614","title":"Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements","created":"2024-02-16","cited_by_count":34,"area":null},{"id":"2410.21252","title":"LongReward: Improving Long-context Large Language Models with AI Feedback","created":"2024-10-28","cited_by_count":34,"area":"alignment"},{"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":"2503.17489","title":"Judge Anything: MLLM as a Judge Across Any Modality","created":"2025-03-21","cited_by_count":34,"area":null},{"id":"2506.23235","title":"Generalist Reward Models: Found Inside Large Language Models","created":"2025-06-29","cited_by_count":34,"area":"alignment"},{"id":"2507.05255","title":"Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning","created":"2025-07-07","cited_by_count":34,"area":"lr"},{"id":"2405.15143","title":"Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models","created":"2024-05-24","cited_by_count":33,"area":null},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2505.20075","title":"Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback","created":"2025-05-26","cited_by_count":32,"area":"alignment"},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2510.15831","title":"VISTA: A Test-Time Self-Improving Video Generation Agent","created":"2025-10-17","cited_by_count":31,"area":null},{"id":"2312.13951","title":"Typhoon: Thai Large Language Models","created":"2023-12-21","cited_by_count":30,"area":null},{"id":"2502.18008","title":"NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms","created":"2025-02-25","cited_by_count":30,"area":null}],"next_cursor":"100"}