{"total":62,"rows":[{"id":"2504.20571","title":"Reinforcement Learning for Reasoning in Large Language Models with One Training Example","created":"2025-04-29","cited_by_count":295,"area":"lr"},{"id":"2506.02177","title":"Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts","created":"2025-06-02","cited_by_count":113,"area":"lr"},{"id":"2405.21046","title":"Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF","created":"2024-05-31","cited_by_count":106,"area":"alignment"},{"id":"2503.21878","title":"Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment","created":"2025-03-27","cited_by_count":97,"area":"alignment"},{"id":"2407.13399","title":"Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization","created":"2024-07-18","cited_by_count":78,"area":"alignment"},{"id":"2503.15477","title":"What Makes a Reward Model a Good Teacher? An Optimization Perspective","created":"2025-03-19","cited_by_count":73,"area":"alignment"},{"id":"2510.01135","title":"Prompt Curriculum Learning for Efficient LLM Post-Training","created":"2025-10-01","cited_by_count":45,"area":null},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2503.06358","title":"Language Model Personalization via Reward Factorization","created":"2025-03-08","cited_by_count":31,"area":"alignment"},{"id":"2407.13977","title":"A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits","created":"2024-07-19","cited_by_count":29,"area":null},{"id":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","cited_by_count":17,"area":null},{"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":"2506.17252","title":"Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization","created":"2025-06-08","cited_by_count":17,"area":"alignment"},{"id":"2505.14826","title":"FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain","created":"2025-05-20","cited_by_count":15,"area":null},{"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":"2504.03784","title":"Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning","created":"2025-04-03","cited_by_count":13,"area":"alignment"},{"id":"2506.02281","title":"Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals","created":"2025-06-02","cited_by_count":13,"area":null},{"id":"2505.19281","title":"A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning","created":"2025-05-25","cited_by_count":11,"area":"deeprl"},{"id":"2602.08499","title":"Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards","created":"2026-02-09","cited_by_count":11,"area":"lr"},{"id":"2503.01076","title":"Active Learning for Direct Preference Optimization","created":"2025-03-03","cited_by_count":10,"area":"alignment"},{"id":"2505.19241","title":"ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment","created":"2025-05-25","cited_by_count":10,"area":"lr"},{"id":"2507.06573","title":"From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimization","created":"2025-07-09","cited_by_count":10,"area":"lr"},{"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":"2507.07981","title":"Why is Your Language Model a Poor Implicit Reward Model?","created":"2025-07-10","cited_by_count":6,"area":"alignment"},{"id":"2511.02966","title":"Inference-Time Personalized Alignment with a Few User Preference Queries","created":"2025-11-04","cited_by_count":6,"area":null},{"id":"2601.08421","title":"Coverage Improvement and Fast Convergence of On-policy Preference Learning","created":"2026-01-13","cited_by_count":6,"area":"alignment"},{"id":"2412.19396","title":"Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe","created":"2024-12-27","cited_by_count":5,"area":"alignment"},{"id":"2510.04072","title":"Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning","created":"2025-10-05","cited_by_count":4,"area":"lr"},{"id":"2604.02507","title":"Reinforcement Learning from Human Feedback: A Statistical Perspective","created":"2026-04-02","cited_by_count":4,"area":"alignment"},{"id":"2410.15610","title":"On The Global Convergence Of Online RLHF With Neural Parametrization","created":"2024-10-21","cited_by_count":3,"area":"alignment"},{"id":"2411.00524","title":"Comparison-based Active Preference Learning for Multi-dimensional Personalization","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2505.23673","title":"Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds","created":"2025-05-29","cited_by_count":3,"area":"alignment"},{"id":"2506.09508","title":"Efficient Preference-Based Reinforcement Learning: Randomized Exploration Meets Experimental Design","created":"2025-06-11","cited_by_count":3,"area":"alignment"},{"id":"2509.23371","title":"Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization","created":"2025-09-27","cited_by_count":3,"area":"alignment"},{"id":"2510.13022","title":"On the Role of Preference Variance in Preference Optimization","created":"2025-10-14","cited_by_count":3,"area":"alignment"},{"id":"2602.10286","title":"What Does Preference Learning Recover from Pairwise Comparison Data?","created":"2026-02-10","cited_by_count":3,"area":"alignment"},{"id":"2602.24040","title":"RewardUQ: A Unified Framework for Uncertainty-Aware Reward Models","created":"2026-02-27","cited_by_count":3,"area":"alignment"},{"id":"2603.22563","title":"Privacy-Preserving Reinforcement Learning from Human Feedback via Decoupled Reward Modeling","created":"2026-03-23","cited_by_count":3,"area":"alignment"},{"id":"2604.17501","title":"CoAct: Co-Active LLM Preference Learning with Human-AI Synergy","created":"2026-04-19","cited_by_count":3,"area":"alignment"},{"id":"2509.03672","title":"SharedRep-RLHF: A Shared Representation Approach to RLHF with Diverse Preferences","created":"2025-09-03","cited_by_count":2,"area":"alignment"},{"id":"2510.03269","title":"General Exploratory Bonus for Optimistic Exploration in RLHF","created":"2025-09-27","cited_by_count":2,"area":"alignment"},{"id":"2510.18713","title":"Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options","created":"2025-10-21","cited_by_count":2,"area":"alignment"},{"id":"2602.00603","title":"Direct Preference Optimization with Rating Information: Practical Algorithms and Provable Gains","created":"2026-01-31","cited_by_count":2,"area":"alignment"},{"id":"2602.03452","title":"Beyond Variance: Prompt-Efficient RLVR via Rare-Event Amplification and Bidirectional Pairing","created":"2026-02-03","cited_by_count":2,"area":"lr"},{"id":"2602.20132","title":"LAD: Learning Advantage Distribution for Reasoning","created":"2026-02-23","cited_by_count":2,"area":"lr"},{"id":"2510.14315","title":"Active Measuring in Reinforcement Learning With Delayed Negative Effects","created":"2025-10-16","cited_by_count":1,"area":"deeprl"},{"id":"2601.20666","title":"Learning Contextual Runtime Monitors for Safe AI-Based Autonomy","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2605.10784","title":"MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization","created":"2026-05-11","cited_by_count":1,"area":"alignment"},{"id":"2605.20408","title":"Spectral Souping: A Unified Framework for Online Preference Alignment","created":"2026-05-19","cited_by_count":1,"area":"alignment"},{"id":"2605.24803","title":"Active Learning for Stochastic Contextual Linear Bandits","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2506.08965","title":"GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO","created":"2025-06-10","cited_by_count":0,"area":"alignment"},{"id":"2510.26301","title":"Offline Clustering of Preference Learning with Active-data Augmentation","created":"2025-10-30","cited_by_count":0,"area":"alignment"},{"id":"2511.12867","title":"Bootstrapping LLMs via Preference-Based Policy Optimization","created":"2025-11-17","cited_by_count":0,"area":"alignment"},{"id":"2602.01581","title":"Nearly Optimal Active Preference Learning and Its Application to LLM Alignment","created":"2026-02-02","cited_by_count":0,"area":"alignment"},{"id":"2602.06239","title":"Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution","created":"2026-02-05","cited_by_count":0,"area":"alignment"},{"id":"2602.08819","title":"Bayesian Preference Learning for Test-Time Steerable Reward Models","created":"2026-02-09","cited_by_count":0,"area":"alignment"},{"id":"2603.17378","title":"Efficient Exploration at Scale","created":"2026-03-18","cited_by_count":0,"area":"alignment"},{"id":"2603.19294","title":"Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2605.00155","title":"Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback","created":"2026-04-30","cited_by_count":0,"area":"alignment"},{"id":"2606.01382","title":"Efficient Exploration for Iterative Nash Preference Optimization","created":"2026-05-31","cited_by_count":0,"area":"alignment"},{"id":"2608.15402","title":"Towards a theory of inference-time alignment with unknown rewards","created":"2026-08-15","cited_by_count":0,"area":"alignment"},{"id":"2610.17203","title":"Online LLM Personalization from Pairwise Preferences Across Users","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}