{"total":102,"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":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144,"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":"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":"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":"2111.12306","title":"Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability","created":"2021-11-24","cited_by_count":44,"area":null},{"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":"2202.04593","title":"Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models","created":"2022-02-09","cited_by_count":37,"area":null},{"id":"2303.03751","title":"Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles","created":"2023-03-07","cited_by_count":35,"area":"alignment"},{"id":"2202.01651","title":"A Survey of Methods for Automated Algorithm Configuration","created":"2022-02-03","cited_by_count":30,"area":null},{"id":"2303.15746","title":"qEUBO: A Decision-Theoretic Acquisition Function for Preferential Bayesian Optimization","created":"2023-03-28","cited_by_count":23,"area":null},{"id":"2310.00968","title":"Variance-Aware Regret Bounds for Stochastic Contextual Dueling Bandits","created":"2023-10-02","cited_by_count":22,"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":"2312.00267","title":"Sample Efficient Preference Alignment in LLMs via Active Exploration","created":"2023-12-01","cited_by_count":18,"area":"alignment"},{"id":"2303.08816","title":"Borda Regret Minimization for Generalized Linear Dueling Bandits","created":"2023-03-15","cited_by_count":17,"area":null},{"id":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2302.03683","title":"Linear Partial Monitoring for Sequential Decision-Making: Algorithms, Regret Bounds and Applications","created":"2023-02-07","cited_by_count":12,"area":null},{"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":"2105.11802","title":"Bias-Robust Bayesian Optimization via Dueling Bandits","created":"2021-05-25","cited_by_count":11,"area":null},{"id":"2203.06063","title":"Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons","created":"2022-03-11","cited_by_count":10,"area":null},{"id":"2505.19241","title":"ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment","created":"2025-05-25","cited_by_count":10,"area":"lr"},{"id":"2111.03917","title":"Optimal and Efficient Dynamic Regret Algorithms for Non-Stationary Dueling Bandits","created":"2021-11-06","cited_by_count":9,"area":null},{"id":"2210.07773","title":"Diversified Recommendations for Agents with Adaptive Preferences","created":"2022-09-20","cited_by_count":9,"area":null},{"id":"2503.13817","title":"VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences","created":"2025-03-18","cited_by_count":9,"area":"mllm"},{"id":"2210.14322","title":"ANACONDA: An Improved Dynamic Regret Algorithm for Adaptive Non-Stationary Dueling Bandits","created":"2022-10-25","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":"2503.00924","title":"PABBO: Preferential Amortized Black-Box Optimization","created":"2025-03-02","cited_by_count":8,"area":null},{"id":"2510.13907","title":"LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization","created":"2025-10-14","cited_by_count":8,"area":null},{"id":"2202.00935","title":"Non-Stationary Dueling Bandits","created":"2022-02-02","cited_by_count":7,"area":null},{"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":"2310.16252","title":"Near-Optimal Pure Exploration in Matrix Games: A Generalization of Stochastic Bandits & Dueling Bandits","created":"2023-10-25","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":"2407.17112","title":"Neural Dueling Bandits: Preference-Based Optimization with Human Feedback","created":"2024-07-24","cited_by_count":7,"area":"alignment"},{"id":"2504.18026","title":"Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization","created":"2025-04-25","cited_by_count":7,"area":"alignment"},{"id":"2210.02562","title":"Dueling Convex Optimization with General Preferences","created":"2022-09-27","cited_by_count":6,"area":null},{"id":"2212.00333","title":"AC-Band: A Combinatorial Bandit-Based Approach to Algorithm Configuration","created":"2022-12-01","cited_by_count":6,"area":null},{"id":"2306.02628","title":"Active Ranking of Experts Based on their Performances in Many Tasks","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2405.03059","title":"Active Preference Learning for Ordering Items In- and Out-of-sample","created":"2024-05-05","cited_by_count":6,"area":null},{"id":"2406.09574","title":"Online Bandit Learning with Offline Preference Data for Improved RLHF","created":"2024-06-13","cited_by_count":6,"area":"alignment"},{"id":"2502.14581","title":"A Statistical Case Against Empirical Human-AI Alignment","created":"2025-02-20","cited_by_count":6,"area":null},{"id":"2601.16403","title":"Towards a Theoretical Understanding to the Generalization of RLHF","created":"2026-01-23","cited_by_count":6,"area":"alignment"},{"id":"2202.04487","title":"Finding Optimal Arms in Non-stochastic Combinatorial Bandits with Semi-bandit Feedback and Finite Budget","created":"2022-02-09","cited_by_count":5,"area":null},{"id":"2202.06694","title":"Versatile Dueling Bandits: Best-of-both-World Analyses for Online Learning from Preferences","created":"2022-02-14","cited_by_count":5,"area":null},{"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":"2307.11288","title":"Kernelized Offline Contextual Dueling Bandits","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2402.18917","title":"Stop Relying on No-Choice and Do not Repeat the Moves: Optimal, Efficient and Practical Algorithms for Assortment Optimization","created":"2024-02-29","cited_by_count":4,"area":null},{"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":"2504.12016","title":"Active Human Feedback Collection via Neural Contextual Dueling Bandits","created":"2025-04-16","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":"2205.13255","title":"Active Labeling: Streaming Stochastic Gradients","created":"2022-05-26","cited_by_count":3,"area":null},{"id":"2210.14998","title":"One Arrow, Two Kills: An Unified Framework for Achieving Optimal Regret Guarantees in Sleeping Bandits","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2312.11788","title":"Faster Convergence with Multiway Preferences","created":"2023-12-19","cited_by_count":3,"area":null},{"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":"2406.14699","title":"Preferential Multi-Objective Bayesian Optimization","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2408.14603","title":"Biased Dueling Bandits with Stochastic Delayed Feedback","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2409.05798","title":"Enhancing Preference-based Linear Bandits via Human Response Time","created":"2024-09-09","cited_by_count":3,"area":null},{"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":"2505.23673","title":"Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds","created":"2025-05-29","cited_by_count":3,"area":"alignment"},{"id":"2403.12950","title":"Non-Stationary Dueling Bandits Under a Weighted Borda Criterion","created":"2024-03-19","cited_by_count":2,"area":null},{"id":"2405.11204","title":"Learning from Imperfect Human Feedback: a Tale from Corruption-Robust Dueling","created":"2024-05-18","cited_by_count":2,"area":"alignment"},{"id":"2507.11706","title":"Reinforcement Learning from Adversarial Preferences in Tabular MDPs","created":"2025-07-15","cited_by_count":2,"area":"deeprl"},{"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":"2602.21585","title":"Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences","created":"2026-02-25","cited_by_count":2,"area":"lr"},{"id":"2603.09692","title":"ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2608.15050","title":"Online Convex Optimization with Dueling Feedback","created":"2026-08-15","cited_by_count":2,"area":null},{"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":"2502.20033","title":"Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization","created":"2025-02-27","cited_by_count":1,"area":null},{"id":"2505.22820","title":"Preference Learning with Response Time: Robust Losses and Guarantees","created":"2025-05-28","cited_by_count":1,"area":"alignment"},{"id":"2604.00523","title":"Lipschitz Dueling Bandits over Continuous Action Spaces","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2604.22161","title":"Logistic Bandits with $\\tilde{O}(\\sqrt{dT})$ Regret without Context Diversity Assumptions","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2107.02738","title":"Dueling Bandits with Team Comparisons","created":"2021-07-06","cited_by_count":0,"area":null},{"id":"2310.00750","title":"Identifying Copeland Winners in Dueling Bandits with Indifferences","created":"2023-10-01","cited_by_count":0,"area":null},{"id":"2311.14003","title":"Direct Preference-Based Evolutionary Multi-Objective Optimization with Dueling Bandit","created":"2023-11-23","cited_by_count":0,"area":null},{"id":"2312.11663","title":"Eliciting Kemeny Rankings","created":"2023-12-18","cited_by_count":0,"area":null},{"id":"2403.06100","title":"Automatic design optimization of preference-based subjective evaluation with online learning in crowdsourcing environment","created":"2024-03-10","cited_by_count":0,"area":null},{"id":"2408.06257","title":"Reciprocal Learning","created":"2024-08-12","cited_by_count":0,"area":null},{"id":"2502.17077","title":"A comparative analysis of rank aggregation methods for the partial label ranking problem","created":"2025-02-24","cited_by_count":0,"area":null},{"id":"2505.23927","title":"Thompson Sampling in Online RLHF with General Function Approximation","created":"2025-05-29","cited_by_count":0,"area":"alignment"},{"id":"2508.05367","title":"Latent Preference Bandits","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2508.18841","title":"Recycling History: Efficient Recommendations from Contextual Dueling Bandits","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2510.26301","title":"Offline Clustering of Preference Learning with Active-data Augmentation","created":"2025-10-30","cited_by_count":0,"area":"alignment"},{"id":"2512.14263","title":"DT-PBO: an Interpretable Tree-based Surrogate Model for Preferential Bayesian Optimization","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2512.21111","title":"Statistical and computational challenges in ranking","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2602.08244","title":"Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers","created":"2026-02-09","cited_by_count":0,"area":"alignment"},{"id":"2604.17747","title":"Efficient Federated RLHF via Zeroth-Order Policy Optimization","created":"2026-04-20","cited_by_count":0,"area":"alignment"},{"id":"2604.25025","title":"A Finite Time Analysis of Thompson Sampling for Bayesian Optimization with Preferential Feedback","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.07304","title":"Latent Order Bandits","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.15697","title":"Distributed Zeroth-Order Policy Gradient for Networked Multi-agent Reinforcement Learning from Human Feedback","created":"2026-05-15","cited_by_count":0,"area":"alignment"},{"id":"2605.23650","title":"Learning Kernel-Based MDPs from Episodic Preferential Feedback","created":"2026-05-22","cited_by_count":0,"area":"alignment"},{"id":"2606.01799","title":"Tree-Guided Identify-Then-Exploit: A Unified Framework of Best Arm Identification and Regret Minimization for Dueling Bandits","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.18933","title":"Zero-Shot Active Feature Acquisition via LLM-Elicitation","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.08979","title":"Optimal Top-$k$ Identification from Pairwise Comparisons","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.01545","title":"Dominant Arm Identification with Mixing and Recycling Observed Samples","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2609.30360","title":"Cost-Aware Best-LLM Identification using Dueling Feedback","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.39351","title":"On the Complexity of Preference-Based Bandits","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":"100"}