{"total":106,"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":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912,"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":"2311.13231","title":"Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model","created":"2023-11-22","cited_by_count":252,"area":"diffusion"},{"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":"2312.00886","title":"Nash Learning from Human Feedback","created":"2023-12-01","cited_by_count":224,"area":"alignment"},{"id":"2402.10207","title":"Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment","created":"2024-02-15","cited_by_count":175,"area":"alignment"},{"id":"2403.00409","title":"Provably Robust DPO: Aligning Language Models with Noisy Feedback","created":"2024-03-01","cited_by_count":135,"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":"2501.13926","title":"Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step","created":"2025-01-23","cited_by_count":131,"area":"lr"},{"id":"2404.18922","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","created":"2024-04-29","cited_by_count":127,"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":"2405.21046","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":"2306.14111","title":"Is RLHF More Difficult than Standard RL?","created":"2023-06-25","cited_by_count":96,"area":"alignment"},{"id":"2205.11140","title":"Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation","created":"2022-05-23","cited_by_count":81,"area":null},{"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":"2305.18438","title":"Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism","created":"2023-05-29","cited_by_count":69,"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":"2402.10500","title":"Active Preference Optimization for Sample Efficient RLHF","created":"2024-02-16","cited_by_count":62,"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":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55,"area":null},{"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":"2310.14554","title":"Making RL with Preference-based Feedback Efficient via Randomization","created":"2023-10-23","cited_by_count":46,"area":"alignment"},{"id":"2402.06886","title":"Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF","created":"2024-02-10","cited_by_count":41,"area":"alignment"},{"id":"2404.08495","title":"Dataset Reset Policy Optimization for RLHF","created":"2024-04-12","cited_by_count":41,"area":"alignment"},{"id":"2308.02585","title":"PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback","created":"2023-08-03","cited_by_count":40,"area":"alignment"},{"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"},{"id":"2305.18505","title":"Provable Reward-Agnostic Preference-Based Reinforcement Learning","created":"2023-05-29","cited_by_count":25,"area":"alignment"},{"id":"2402.10342","title":"Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization","created":"2024-02-15","cited_by_count":25,"area":"alignment"},{"id":"2410.17055","title":"Optimal Design for Reward Modeling in RLHF","created":"2024-10-22","cited_by_count":25,"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":"2402.06734","title":"Corruption Robust Offline Reinforcement Learning with Human Feedback","created":"2024-02-09","cited_by_count":20,"area":"alignment"},{"id":"2402.10893","title":"RLVF: Learning from Verbal Feedback without Overgeneralization","created":"2024-02-16","cited_by_count":19,"area":"alignment"},{"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":"2406.04274","title":"Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models","created":"2024-06-06","cited_by_count":16,"area":"alignment"},{"id":"2206.06426","title":"Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward","created":"2022-06-13","cited_by_count":13,"area":"offlinerl"},{"id":"2307.12975","title":"Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems","created":"2023-07-24","cited_by_count":13,"area":"alignment"},{"id":"2407.18676","title":"Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift","created":"2024-07-26","cited_by_count":13,"area":"alignment"},{"id":"2310.19733","title":"Differentially Private Reward Estimation with Preference Feedback","created":"2023-10-30","cited_by_count":12,"area":"alignment"},{"id":"2409.17401","title":"Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference","created":"2024-09-25","cited_by_count":12,"area":"alignment"},{"id":"2510.24700","title":"Greedy Sampling Is Provably Efficient for RLHF","created":"2025-10-28","cited_by_count":11,"area":"alignment"},{"id":"2405.07637","title":"Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback","created":"2024-05-13","cited_by_count":10,"area":"deeprl"},{"id":"2405.19697","title":"Bilevel reinforcement learning via the development of hyper-gradient without lower-level convexity","created":"2024-05-30","cited_by_count":10,"area":"deeprl"},{"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":"2310.06113","title":"When is Agnostic Reinforcement Learning Statistically Tractable?","created":"2023-10-09","cited_by_count":9,"area":null},{"id":"2410.23569","title":"RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning","created":"2024-10-31","cited_by_count":9,"area":"alignment"},{"id":"2408.11943","title":"Advances in Preference-based Reinforcement Learning: A Review","created":"2024-08-21","cited_by_count":8,"area":"deeprl"},{"id":"2410.01112","title":"Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits","created":"2024-10-01","cited_by_count":8,"area":null},{"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":"2505.15694","title":"A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO","created":"2025-05-21","cited_by_count":8,"area":"alignment"},{"id":"2302.03805","title":"Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback","created":"2023-02-07","cited_by_count":7,"area":null},{"id":"2406.16745","title":"Bandits with Preference Feedback: A Stackelberg Game Perspective","created":"2024-06-24","cited_by_count":7,"area":"alignment"},{"id":"2504.19342","title":"Contextual Online Uncertainty-Aware Preference Learning for Human Feedback","created":"2025-04-27","cited_by_count":7,"area":"alignment"},{"id":"2505.20268","title":"Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits","created":"2025-05-26","cited_by_count":7,"area":"deeprl"},{"id":"2601.16403","title":"Towards a Theoretical Understanding to the Generalization of RLHF","created":"2026-01-23","cited_by_count":6,"area":"alignment"},{"id":"2407.18488","title":"Conversational Dueling Bandits in Generalized Linear Models","created":"2024-07-26","cited_by_count":5,"area":null},{"id":"2501.18873","title":"Best Policy Learning from Trajectory Preference Feedback","created":"2025-01-31","cited_by_count":5,"area":"alignment"},{"id":"2602.23116","title":"Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences","created":"2026-02-26","cited_by_count":5,"area":"alignment"},{"id":"2307.11897","title":"Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2312.00054","title":"Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective","created":"2023-11-29","cited_by_count":4,"area":"offlinerl"},{"id":"2406.07455","title":"Reinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis","created":"2024-06-11","cited_by_count":4,"area":"alignment"},{"id":"2502.05434","title":"Sample-Efficient Reinforcement Learning from Human Feedback via Information-Directed Sampling","created":"2025-02-08","cited_by_count":4,"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":"2502.19255","title":"Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective","created":"2025-02-26","cited_by_count":4,"area":"alignment"},{"id":"2503.19201","title":"A Shared Low-Rank Adaptation Approach to Personalized RLHF","created":"2025-03-24","cited_by_count":4,"area":"alignment"},{"id":"2506.03066","title":"Sign-SZPO: Provable Preference-based Reinforcement Learning with an Unknown Link Function","created":"2025-06-03","cited_by_count":4,"area":"deeprl"},{"id":"2510.08539","title":"On the optimization dynamics of RLVR: Gradient gap and step size thresholds","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2311.01990","title":"Conditions on Preference Relations that Guarantee the Existence of Optimal Policies","created":"2023-11-03","cited_by_count":3,"area":"alignment"},{"id":"2312.17229","title":"Think Before You Duel: Understanding Complexities of Preference Learning under Constrained Resources","created":"2023-12-28","cited_by_count":3,"area":null},{"id":"2406.18450","title":"Preference Elicitation for Offline Reinforcement Learning","created":"2024-06-26","cited_by_count":3,"area":"offlinerl"},{"id":"2501.18282","title":"Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective","created":"2025-01-30","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":"2510.13022","title":"On the Role of Preference Variance in Preference Optimization","created":"2025-10-14","cited_by_count":3,"area":"alignment"},{"id":"2307.12926","title":"Contextual Bandits and Imitation Learning via Preference-Based Active Queries","created":"2023-07-24","cited_by_count":2,"area":"offlinerl"},{"id":"2310.15694","title":"COPR: Continual Learning Human Preference through Optimal Policy Regularization","created":"2023-10-24","cited_by_count":2,"area":"alignment"},{"id":"2410.05527","title":"DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback","created":"2024-10-07","cited_by_count":2,"area":"alignment"},{"id":"2503.05306","title":"Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2507.11706","title":"Reinforcement Learning from Adversarial Preferences in Tabular MDPs","created":"2025-07-15","cited_by_count":2,"area":"deeprl"},{"id":"2507.20067","title":"PITA: Preference-Guided Inference-Time Alignment for LLM Post-Training","created":"2025-07-26","cited_by_count":2,"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":"2510.18713","title":"Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options","created":"2025-10-21","cited_by_count":2,"area":"alignment"},{"id":"2603.19221","title":"Online Learning and Equilibrium Computation with Ranking Feedback","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2310.03108","title":"Reinforcement Learning-based Mixture of Vision Transformers for Video Violence Recognition","created":"2023-10-04","cited_by_count":1,"area":"moe"},{"id":"2402.03282","title":"A Theoretical Framework for Partially Observed Reward-States in RLHF","created":"2024-02-05","cited_by_count":1,"area":"alignment"},{"id":"2403.15045","title":"DP-Dueling: Learning from Preference Feedback without Compromising User Privacy","created":"2024-03-22","cited_by_count":1,"area":null},{"id":"2604.00200","title":"Offline Constrained RLHF with Multiple Preference Oracles","created":"2026-03-31","cited_by_count":1,"area":"alignment"},{"id":"2605.02495","title":"Efficient Preference Poisoning Attack on Offline RLHF","created":"2026-05-04","cited_by_count":1,"area":"alignment"},{"id":"2605.12545","title":"CROP: Expert-Aligned Image Cropping via Compositional Reasoning and Optimizing Preference","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2606.27082","title":"Finding Stationary Points by Comparisons","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2310.10556","title":"Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks","created":"2023-10-16","cited_by_count":0,"area":"alignment"},{"id":"2407.06503","title":"Preference-Guided Reinforcement Learning for Efficient Exploration","created":"2024-07-09","cited_by_count":0,"area":"deeprl"},{"id":"2504.14732","title":"Reinforcement Learning from Multi-level and Episodic Human Feedback","created":"2025-04-20","cited_by_count":0,"area":"alignment"},{"id":"2505.06601","title":"Learning Guarantee of Reward Modeling Using Deep Neural Networks","created":"2025-05-10","cited_by_count":0,"area":"alignment"},{"id":"2505.23927","title":"Thompson Sampling in Online RLHF with General Function Approximation","created":"2025-05-29","cited_by_count":0,"area":"alignment"},{"id":"2512.19057","title":"Efficient Personalization of Generative Models via Optimal Experimental Design","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2601.19055","title":"Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward","created":"2026-01-27","cited_by_count":0,"area":null}],"next_cursor":"100"}