{"total":96,"rows":[{"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":"2405.00675","title":"Self-Play Preference Optimization for Language Model Alignment","created":"2024-05-01","cited_by_count":232,"area":"alignment"},{"id":"2312.00886","title":"Nash Learning from Human Feedback","created":"2023-12-01","cited_by_count":224,"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":"2408.10075","title":"Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning","created":"2024-08-19","cited_by_count":155,"area":"alignment"},{"id":"2402.18571","title":"Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards","created":"2024-02-28","cited_by_count":148,"area":"alignment"},{"id":"2404.18922","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","created":"2024-04-29","cited_by_count":127,"area":"alignment"},{"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":"2406.14532","title":"RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold","created":"2024-06-20","cited_by_count":99,"area":"lr"},{"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":"2404.16767","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","created":"2024-04-25","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":"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":"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":"2402.09401","title":"Reinforcement Learning from Human Feedback with Active Queries","created":"2024-02-14","cited_by_count":43,"area":"alignment"},{"id":"2406.06852","title":"A Survey of Recent Backdoor Attacks and Defenses in Large Language Models","created":"2024-06-10","cited_by_count":36,"area":"safety"},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"area":"alignment"},{"id":"2410.04612","title":"Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF","created":"2024-10-06","cited_by_count":30,"area":"alignment"},{"id":"2410.02197","title":"Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment","created":"2024-10-03","cited_by_count":27,"area":"alignment"},{"id":"2410.17055","title":"Optimal Design for Reward Modeling in RLHF","created":"2024-10-22","cited_by_count":25,"area":"alignment"},{"id":"2412.03578","title":"PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback","created":"2024-11-18","cited_by_count":24,"area":null},{"id":"2502.07460","title":"Logarithmic Regret for Online KL-Regularized Reinforcement Learning","created":"2025-02-11","cited_by_count":22,"area":"alignment"},{"id":"2505.23749","title":"Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?","created":"2025-05-29","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":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2402.05367","title":"Principled Preferential Bayesian Optimization","created":"2024-02-08","cited_by_count":16,"area":null},{"id":"2503.08942","title":"Extragradient Preference Optimization (EGPO): Beyond Last-Iterate Convergence for Nash Learning from Human Feedback","created":"2025-03-11","cited_by_count":16,"area":"alignment"},{"id":"2403.18742","title":"Understanding the Learning Dynamics of Alignment with Human Feedback","created":"2024-03-27","cited_by_count":15,"area":"alignment"},{"id":"2307.02842","title":"Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback","created":"2023-07-06","cited_by_count":14,"area":"alignment"},{"id":"2412.09544","title":"Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking","created":"2024-12-12","cited_by_count":13,"area":"alignment"},{"id":"2404.03745","title":"Fakes of Varying Shades: How Warning Affects Human Perception and Engagement Regarding LLM Hallucinations","created":"2024-04-04","cited_by_count":12,"area":null},{"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":"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":"2504.21304","title":"Unsupervised Feature Transformation via In-context Generation, Generator-critic LLM Agents, and Duet-play Teaming","created":"2025-04-30","cited_by_count":11,"area":"agents"},{"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":"2310.17303","title":"Demonstration-Regularized RL","created":"2023-10-26","cited_by_count":9,"area":"alignment"},{"id":"2503.04783","title":"Comparative Analysis Based on DeepSeek, ChatGPT, and Google Gemini: Features, Techniques, Performance, Future Prospects","created":"2025-02-25","cited_by_count":9,"area":"lr"},{"id":"2506.09420","title":"A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy","created":"2025-06-11","cited_by_count":9,"area":"agents"},{"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":"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":"2412.10616","title":"Hybrid Preference Optimization for Alignment: Provably Faster Convergence Rates by Combining Offline Preferences with Online Exploration","created":"2024-12-13","cited_by_count":6,"area":"alignment"},{"id":"2502.00657","title":"LLM Safety Alignment is Divergence Estimation in Disguise","created":"2025-02-02","cited_by_count":6,"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":"2601.08421","title":"Coverage Improvement and Fast Convergence of On-policy Preference Learning","created":"2026-01-13","cited_by_count":6,"area":"alignment"},{"id":"2510.22095","title":"Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologies","created":"2025-10-25","cited_by_count":5,"area":"agents"},{"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":"2502.06861","title":"Design Considerations in Offline Preference-based RL","created":"2025-02-08","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":"2602.09456","title":"Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits","created":"2026-02-10","cited_by_count":4,"area":null},{"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":"2502.12678","title":"Multi-Step Alignment as Markov Games: An Optimistic Online Gradient Descent Approach with Convergence Guarantees","created":"2025-02-18","cited_by_count":3,"area":"alignment"},{"id":"2505.21395","title":"Square$\\chi$PO: Differentially Private and Robust $\\chi^2$-Preference Optimization in Offline Direct Alignment","created":"2025-05-27","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":"2606.06053","title":"Online KL-Regularized Reinforcement Learning with Function Approximation under Misspecification","created":"2026-06-04","cited_by_count":3,"area":"deeprl"},{"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":"2505.11983","title":"Online Iterative Self-Alignment for Radiology Report Generation","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2510.23965","title":"The Sign Estimator: LLM Alignment in the Face of Choice Heterogeneity","created":"2025-10-28","cited_by_count":2,"area":"alignment"},{"id":"2601.04670","title":"Learning Dynamics in RL Post-Training for Language Models","created":"2026-01-08","cited_by_count":2,"area":"lr"},{"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":"2403.08199","title":"Deep Submodular Peripteral Networks","created":"2024-03-13","cited_by_count":1,"area":null},{"id":"2406.10445","title":"Binary Reward Labeling: Bridging Offline Preference and Reward-Based Reinforcement Learning","created":"2024-06-14","cited_by_count":1,"area":"alignment"},{"id":"2410.11444","title":"A Theoretical Survey on Foundation Models","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2410.14715","title":"Animating the Past: Reconstruct Trilobite via Video Generation","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2504.15812","title":"Fusing Reward and Dueling Feedback in Stochastic Bandits","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2505.19964","title":"The Limits of Preference Data for Post-Training","created":"2025-05-26","cited_by_count":1,"area":"alignment"},{"id":"2510.05526","title":"Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment","created":"2025-10-07","cited_by_count":1,"area":"alignment"},{"id":"2511.00220","title":"Iterative Foundation Model Fine-Tuning on Multiple Rewards","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2603.20453","title":"Regret Bounds for Reinforcement Learning from Multi-Source Imperfect Preferences","created":"2026-03-20","cited_by_count":1,"area":"alignment"},{"id":"2604.00200","title":"Offline Constrained RLHF with Multiple Preference Oracles","created":"2026-03-31","cited_by_count":1,"area":"alignment"},{"id":"2604.21700","title":"Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers","created":"2026-04-23","cited_by_count":1,"area":"safety"},{"id":"2605.02495","title":"Efficient Preference Poisoning Attack on Offline RLHF","created":"2026-05-04","cited_by_count":1,"area":"alignment"},{"id":"2606.27082","title":"Finding Stationary Points by Comparisons","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2412.16378","title":"REFA: Reference Free Alignment for multi-preference optimization","created":"2024-12-20","cited_by_count":0,"area":"alignment"},{"id":"2504.14732","title":"Reinforcement Learning from Multi-level and Episodic Human Feedback","created":"2025-04-20","cited_by_count":0,"area":"alignment"},{"id":"2505.23927","title":"Thompson Sampling in Online RLHF with General Function Approximation","created":"2025-05-29","cited_by_count":0,"area":"alignment"},{"id":"2506.01692","title":"A Descriptive and Normative Theory of Human Beliefs in RLHF","created":"2025-06-02","cited_by_count":0,"area":"alignment"},{"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},{"id":"2604.02349","title":"OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2604.17207","title":"Demystifying the unreasonable effectiveness of online alignment methods","created":"2026-04-19","cited_by_count":0,"area":"alignment"},{"id":"2605.23244","title":"Convex Optimization for Alignment and Preference Learning on a Single GPU","created":"2026-05-22","cited_by_count":0,"area":"alignment"},{"id":"2606.00367","title":"Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems","created":"2026-05-29","cited_by_count":0,"area":"deeprl"},{"id":"2606.01382","title":"Efficient Exploration for Iterative Nash Preference Optimization","created":"2026-05-31","cited_by_count":0,"area":"alignment"},{"id":"2606.08410","title":"Provably Efficient Personalized Multi-Objective Bandits with Proactive Conversational Queries","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.22652","title":"A Markov Chain Approach to Preference Alignment","created":"2026-06-21","cited_by_count":0,"area":"alignment"},{"id":"2609.38938","title":"Robust Risk-Sensitive Reinforcement Learning from Corrupted Human Feedback","created":"2026-09-30","cited_by_count":0,"area":"alignment"}],"next_cursor":null}