{"total":127,"rows":[{"id":"2406.12845","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","created":"2024-06-18","cited_by_count":376,"area":"alignment"},{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267,"area":"lr"},{"id":"2406.10216","title":"Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs","created":"2024-06-14","cited_by_count":142,"area":"alignment"},{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112,"area":null},{"id":"2405.16436","title":"Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer","created":"2024-05-26","cited_by_count":109,"area":"alignment"},{"id":"2405.20304","title":"Group Robust Preference Optimization in Reward-free RLHF","created":"2024-05-30","cited_by_count":95,"area":"lr"},{"id":"2410.11287","title":"Process Reward Model with Q-Value Rankings","created":"2024-10-15","cited_by_count":80,"area":"lr"},{"id":"2405.19320","title":"Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF","created":"2024-05-29","cited_by_count":73,"area":"alignment"},{"id":"2408.13006","title":"Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates","created":"2024-08-23","cited_by_count":72,"area":"alignment"},{"id":"2502.19613","title":"Self-rewarding correction for mathematical reasoning","created":"2025-02-26","cited_by_count":70,"area":"lr"},{"id":"2409.02392","title":"Building Math Agents with Multi-Turn Iterative Preference Learning","created":"2024-09-04","cited_by_count":66,"area":"lr"},{"id":"2405.19332","title":"Self-Exploring Language Models: Active Preference Elicitation for Online Alignment","created":"2024-05-29","cited_by_count":63,"area":"alignment"},{"id":"2505.16984","title":"UFT: Unifying Supervised and Reinforcement Fine-Tuning","created":"2025-05-22","cited_by_count":59,"area":"lr"},{"id":"2410.08193","title":"GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment","created":"2024-10-10","cited_by_count":54,"area":"alignment"},{"id":"2406.09760","title":"Bootstrapping Language Models with DPO Implicit Rewards","created":"2024-06-14","cited_by_count":53,"area":"alignment"},{"id":"2412.14516","title":"Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment","created":"2024-12-19","cited_by_count":51,"area":"alignment"},{"id":"2412.14135","title":"Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective","created":"2024-12-18","cited_by_count":50,"area":"lr"},{"id":"2509.19199","title":"Agentic Reinforcement Learning with Implicit Step Rewards","created":"2025-09-23","cited_by_count":47,"area":"agents"},{"id":"2505.12929","title":"Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs","created":"2025-05-19","cited_by_count":44,"area":"lr"},{"id":"2412.11006","title":"Entropy-Regularized Process Reward Model","created":"2024-12-15","cited_by_count":38,"area":"lr"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2509.24372","title":"Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning","created":"2025-09-29","cited_by_count":34,"area":null},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"area":"alignment"},{"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":"2506.21656","title":"Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs","created":"2025-06-26","cited_by_count":32,"area":"lr"},{"id":"2503.00897","title":"A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuning","created":"2025-03-02","cited_by_count":30,"area":"diffusion"},{"id":"2409.09345","title":"Enhancing Decision-Making for LLM Agents via Step-Level Q-Value Models","created":"2024-09-14","cited_by_count":28,"area":"agents"},{"id":"2508.19229","title":"StepWiser: Stepwise Generative Judges for Wiser Reasoning","created":"2025-08-26","cited_by_count":28,"area":null},{"id":"2506.08379","title":"Reinforce LLM Reasoning through Multi-Agent Reflection","created":"2025-06-10","cited_by_count":27,"area":"lr"},{"id":"2408.13518","title":"Selective Preference Optimization via Token-Level Reward Function Estimation","created":"2024-08-24","cited_by_count":25,"area":"lr"},{"id":"2406.07327","title":"3D-Properties: Identifying Challenges in DPO and Charting a Path Forward","created":"2024-06-11","cited_by_count":24,"area":"alignment"},{"id":"2505.02391","title":"Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL","created":"2025-05-05","cited_by_count":24,"area":"lr"},{"id":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23,"area":"alignment"},{"id":"2502.07460","title":"Logarithmic Regret for Online KL-Regularized Reinforcement Learning","created":"2025-02-11","cited_by_count":22,"area":"alignment"},{"id":"2502.10581","title":"Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective","created":"2025-02-14","cited_by_count":17,"area":"lr"},{"id":"2503.02832","title":"AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation","created":"2025-03-04","cited_by_count":17,"area":"alignment"},{"id":"2505.23363","title":"Discriminative Policy Optimization for Token-Level Reward Models","created":"2025-05-29","cited_by_count":16,"area":"lr"},{"id":"2504.05782","title":"MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models","created":"2025-04-08","cited_by_count":15,"area":"lr"},{"id":"2505.02666","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","created":"2025-05-05","cited_by_count":15,"area":"alignment"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2502.01208","title":"On Almost Surely Safe Alignment of Large Language Models at Inference-Time","created":"2025-02-03","cited_by_count":14,"area":"alignment"},{"id":"2505.19653","title":"Token-Importance Guided Direct Preference Optimization","created":"2025-05-26","cited_by_count":14,"area":"alignment"},{"id":"2506.22200","title":"EFRame: Deeper Reasoning via Exploration-Filter-Replay Reinforcement Learning Framework","created":"2025-06-27","cited_by_count":14,"area":"lr"},{"id":"2412.02685","title":"T-REG: Preference Optimization with Token-Level Reward Regularization","created":"2024-12-03","cited_by_count":13,"area":"alignment"},{"id":"2410.15483","title":"Understanding Forgetting in LLM Supervised Fine-Tuning and Preference Learning -- A Convex Optimization Perspective","created":"2024-10-20","cited_by_count":12,"area":"alignment"},{"id":"2501.02790","title":"Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model","created":"2025-01-06","cited_by_count":12,"area":"alignment"},{"id":"2510.08141","title":"SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training","created":"2025-10-09","cited_by_count":12,"area":"lr"},{"id":"2507.01551","title":"Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning","created":"2025-07-02","cited_by_count":11,"area":"lr"},{"id":"2510.24700","title":"Greedy Sampling Is Provably Efficient for RLHF","created":"2025-10-28","cited_by_count":11,"area":"alignment"},{"id":"2604.10701","title":"Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning","created":"2026-04-12","cited_by_count":11,"area":null},{"id":"2411.08302","title":"RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution","created":"2024-11-13","cited_by_count":10,"area":"alignment"},{"id":"2412.16834","title":"Online Learning from Strategic Human Feedback in LLM Fine-Tuning","created":"2024-12-22","cited_by_count":10,"area":"alignment"},{"id":"2501.18858","title":"BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning","created":"2025-01-31","cited_by_count":10,"area":"lr"},{"id":"2503.12123","title":"MT-RewardTree: A Comprehensive Framework for Advancing LLM-Based Machine Translation via Reward Modeling","created":"2025-03-15","cited_by_count":10,"area":"lr"},{"id":"2409.00162","title":"Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback","created":"2024-08-30","cited_by_count":9,"area":"alignment"},{"id":"2502.11656","title":"Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL","created":"2025-02-17","cited_by_count":9,"area":"lr"},{"id":"2503.04647","title":"Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment","created":"2025-03-06","cited_by_count":9,"area":"alignment"},{"id":"2502.00666","title":"Avoiding $\\mathbf{exp(R_{max})}$ scaling in RLHF through Preference-based Exploration","created":"2025-02-02","cited_by_count":8,"area":"alignment"},{"id":"2502.03095","title":"Reveal the Mystery of DPO: The Connection between DPO and RL Algorithms","created":"2025-02-05","cited_by_count":8,"area":"alignment"},{"id":"2502.13173","title":"Thinking Preference Optimization","created":"2025-02-17","cited_by_count":8,"area":"lr"},{"id":"2607.17247","title":"Distilled Reinforcement Learning for LLM Post-training","created":"2026-07-19","cited_by_count":8,"area":"distill"},{"id":"2411.00722","title":"Token-level Proximal Policy Optimization for Query Generation","created":"2024-11-01","cited_by_count":7,"area":"alignment"},{"id":"2505.17315","title":"Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2505.19501","title":"Toward Scientific Reasoning in LLMs: Training from Expert Discussions via Reinforcement Learning","created":"2025-05-26","cited_by_count":7,"area":"lr"},{"id":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2602.09331","title":"Beyond Uniform Credit: Causal Credit Assignment for Policy Optimization","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2410.15096","title":"GDPO: Learning to Directly Align Language Models with Diversity Using GFlowNets","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2410.20297","title":"Fine-Tuning and Evaluating Open-Source Large Language Models for the Army Domain","created":"2024-10-27","cited_by_count":6,"area":null},{"id":"2510.09259","title":"Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models","created":"2025-10-10","cited_by_count":6,"area":null},{"id":"2411.10156","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","created":"2024-11-15","cited_by_count":5,"area":"alignment"},{"id":"2502.17927","title":"Advantage-Guided Distillation for Preference Alignment in Small Language Models","created":"2025-02-25","cited_by_count":5,"area":"alignment"},{"id":"2503.04240","title":"DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models","created":"2025-03-06","cited_by_count":5,"area":"alignment"},{"id":"2503.04793","title":"Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference","created":"2025-03-01","cited_by_count":5,"area":"alignment"},{"id":"2503.21383","title":"Controlling Large Language Model with Latent Actions","created":"2025-03-27","cited_by_count":5,"area":null},{"id":"2503.23913","title":"Entropy-Based Adaptive Weighting for Self-Training","created":"2025-03-31","cited_by_count":5,"area":"lr"},{"id":"2504.07527","title":"Supervised Optimism Correction: Be Confident When LLMs Are Sure","created":"2025-04-10","cited_by_count":5,"area":null},{"id":"2506.02553","title":"Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspective","created":"2025-06-03","cited_by_count":5,"area":"alignment"},{"id":"2506.14574","title":"TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization","created":"2025-06-17","cited_by_count":5,"area":"alignment"},{"id":"2502.14560","title":"Less is More: Improving LLM Alignment via Preference Data Selection","created":"2025-02-20","cited_by_count":4,"area":"alignment"},{"id":"2506.13888","title":"VL-GenRM: Enhancing Vision-Language Verification via Vision Experts and Iterative Training","created":"2025-06-16","cited_by_count":4,"area":null},{"id":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"id":"2601.10348","title":"Training-Trajectory-Aware Token Selection","created":"2026-01-15","cited_by_count":4,"area":"lr"},{"id":"2409.18170","title":"Evaluation of Large Language Models for Summarization Tasks in the Medical Domain: A Narrative Review","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2510.13022","title":"On the Role of Preference Variance in Preference Optimization","created":"2025-10-14","cited_by_count":3,"area":"alignment"},{"id":"2604.14646","title":"Targeted Exploration via Unified Entropy Control for Reinforcement Learning","created":"2026-04-16","cited_by_count":3,"area":"lr"},{"id":"2411.00809","title":"Adaptive Segment-level Reward: Bridging the Gap Between Action and Reward Space in Alignment","created":"2024-10-23","cited_by_count":2,"area":"alignment"},{"id":"2504.09488","title":"Kongzi: A Historical Large Language Model with Fact Enhancement","created":"2025-04-13","cited_by_count":2,"area":null},{"id":"2504.16272","title":"Learning Explainable Dense Reward Shapes via Bayesian Optimization","created":"2025-04-22","cited_by_count":2,"area":"alignment"},{"id":"2505.06273","title":"Policy-labeled Preference Learning: Is Preference Enough for RLHF?","created":"2025-05-06","cited_by_count":2,"area":"alignment"},{"id":"2511.23391","title":"Ambiguity Awareness Optimization: Towards Semantic Disambiguation for Direct Preference Optimization","created":"2025-11-28","cited_by_count":2,"area":"alignment"},{"id":"2603.07433","title":"Data Agent: Learning to Select Data via End-to-End Dynamic Optimization","created":"2026-03-08","cited_by_count":2,"area":null},{"id":"2605.07660","title":"Not All Tokens Learn Alike: Attention Entropy Reveals Heterogeneous Signals in RL Reasoning","created":"2026-05-08","cited_by_count":2,"area":"lr"},{"id":"2405.11226","title":"The Power of Active Multi-Task Learning in Reinforcement Learning from Human Feedback","created":"2024-05-18","cited_by_count":1,"area":"alignment"},{"id":"2411.02481","title":"Dr. SoW: Density Ratio of Strong-over-weak LLMs for Reducing the Cost of Human Annotation in Preference Tuning","created":"2024-11-04","cited_by_count":1,"area":"alignment"},{"id":"2502.05773","title":"PIPA: Preference Alignment as Prior-Informed Statistical Estimation","created":"2025-02-09","cited_by_count":1,"area":"alignment"},{"id":"2505.11141","title":"Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans","created":"2025-05-16","cited_by_count":1,"area":"lr"},{"id":"2505.19196","title":"CoCA: Step-level Reward for Free in RL-based T2I Diffusion Model Fine-tuning","created":"2025-05-25","cited_by_count":1,"area":"diffusion"},{"id":"2505.19743","title":"Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models","created":"2025-05-26","cited_by_count":1,"area":"alignment"},{"id":"2508.10839","title":"Reinforced Language Models for Sequential Decision Making","created":"2025-08-14","cited_by_count":1,"area":null}],"next_cursor":"100"}