{"total":101,"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":"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":"2405.00675","title":"Self-Play Preference Optimization for Language Model Alignment","created":"2024-05-01","cited_by_count":232,"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":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144,"area":"alignment"},{"id":"2306.14111","title":"Is RLHF More Difficult than Standard RL?","created":"2023-06-25","cited_by_count":96,"area":"alignment"},{"id":"2404.16767","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","created":"2024-04-25","cited_by_count":69,"area":"alignment"},{"id":"2310.00212","title":"Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment","created":"2023-09-30","cited_by_count":57,"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":"2402.00396","title":"Efficient Exploration for LLMs","created":"2024-02-01","cited_by_count":45,"area":null},{"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":"2402.09401","title":"Reinforcement Learning from Human Feedback with Active Queries","created":"2024-02-14","cited_by_count":43,"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":"2202.04593","title":"Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models","created":"2022-02-09","cited_by_count":37,"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":"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":"2404.06013","title":"Feel-Good Thompson Sampling for Contextual Dueling Bandits","created":"2024-04-09","cited_by_count":27,"area":null},{"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":"2305.18505","title":"Provable Reward-Agnostic Preference-Based Reinforcement Learning","created":"2023-05-29","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":"2310.00968","title":"Variance-Aware Regret Bounds for Stochastic Contextual Dueling Bandits","created":"2023-10-02","cited_by_count":22,"area":null},{"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":"2504.20997","title":"Toward Efficient Exploration by Large Language Model Agents","created":"2025-04-29","cited_by_count":17,"area":"agents"},{"id":"2506.17252","title":"Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization","created":"2025-06-08","cited_by_count":17,"area":"alignment"},{"id":"2402.05367","title":"Principled Preferential Bayesian Optimization","created":"2024-02-08","cited_by_count":16,"area":null},{"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":"2411.01493","title":"Sample-Efficient Alignment for LLMs","created":"2024-11-03","cited_by_count":16,"area":"alignment"},{"id":"2408.14874","title":"Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data","created":"2024-08-27","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":"2202.10660","title":"Batched Dueling Bandits","created":"2022-02-22","cited_by_count":10,"area":null},{"id":"2502.06051","title":"Towards a Sharp Analysis of Offline Policy Learning for $f$-Divergence-Regularized Contextual Bandits","created":"2025-02-09","cited_by_count":10,"area":"offlinerl"},{"id":"2502.17625","title":"Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback","created":"2025-02-24","cited_by_count":10,"area":null},{"id":"2105.01850","title":"Preference learning along multiple criteria: A game-theoretic perspective","created":"2021-05-05","cited_by_count":9,"area":null},{"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":"2404.10776","title":"Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback","created":"2024-04-16","cited_by_count":9,"area":"alignment"},{"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":"2506.12323","title":"Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback","created":"2025-06-14","cited_by_count":9,"area":"alignment"},{"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":"2406.16745","title":"Bandits with Preference Feedback: A Stackelberg Game Perspective","created":"2024-06-24","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":"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":"2601.16403","title":"Towards a Theoretical Understanding to the Generalization of RLHF","created":"2026-01-23","cited_by_count":6,"area":"alignment"},{"id":"2107.02274","title":"Dueling Bandits with Adversarial Sleeping","created":"2021-07-05","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":"2204.04670","title":"Active Learning with Label Comparisons","created":"2022-04-10","cited_by_count":5,"area":null},{"id":"2302.06595","title":"When Can We Track Significant Preference Shifts in Dueling Bandits?","created":"2023-02-13","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":"2410.00362","title":"FedPT: Federated Proxy-Tuning of Large Language Models on Resource-Constrained Edge Devices","created":"2024-10-01","cited_by_count":5,"area":null},{"id":"2410.06293","title":"Accelerated Preference Optimization for Large Language Model Alignment","created":"2024-10-08","cited_by_count":5,"area":"alignment"},{"id":"2602.03876","title":"GOPO: Policy Optimization using Ranked Rewards","created":"2026-02-01","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":"2605.11134","title":"Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training","created":"2026-05-11","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":"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":"2201.09798","title":"IMO$^3$: Interactive Multi-Objective Off-Policy Optimization","created":"2022-01-24","cited_by_count":3,"area":null},{"id":"2202.01879","title":"Learning from a Learning User for Optimal Recommendations","created":"2022-02-03","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":"2408.14603","title":"Biased Dueling Bandits with Stochastic Delayed Feedback","created":"2024-08-26","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":"2602.10286","title":"What Does Preference Learning Recover from Pairwise Comparison Data?","created":"2026-02-10","cited_by_count":3,"area":"alignment"},{"id":"2209.12108","title":"An Asymptotically Optimal Batched Algorithm for the Dueling Bandit Problem","created":"2022-09-25","cited_by_count":2,"area":null},{"id":"2403.12950","title":"Non-Stationary Dueling Bandits Under a Weighted Borda Criterion","created":"2024-03-19","cited_by_count":2,"area":null},{"id":"2407.01887","title":"Beyond Numeric Rewards: In-Context Dueling Bandits with LLM Agents","created":"2024-07-02","cited_by_count":2,"area":"agents"},{"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":"2506.01250","title":"Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration","created":"2025-06-02","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":"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":"2510.21788","title":"Online Mixture of Experts: No-Regret Learning for Optimal Collective Decision-Making","created":"2025-10-19","cited_by_count":2,"area":"moe"},{"id":"2603.09692","title":"ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning","created":"2026-03-10","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":"2606.21550","title":"AI Alignment From Social Choice Perspectives","created":"2026-06-19","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":"2111.03447","title":"Contextual Bayesian optimization with binary outputs","created":"2021-11-05","cited_by_count":1,"area":null},{"id":"2203.16668","title":"Flexible and Efficient Contextual Bandits with Heterogeneous Treatment Effect Oracles","created":"2022-03-30","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":"2406.12205","title":"On the Exponential Convergence for Offline RLHF with Pairwise Comparisons","created":"2024-06-18","cited_by_count":1,"area":"alignment"},{"id":"2406.12475","title":"Adversarial Multi-dueling Bandits","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2503.10215","title":"Adaptive Preference Aggregation","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2510.10077","title":"A-IPO: Adaptive Intent-driven Preference Optimization","created":"2025-10-11","cited_by_count":1,"area":"alignment"},{"id":"2602.21297","title":"Robust AI Evaluation through Maximal Lotteries","created":"2026-02-24","cited_by_count":1,"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":"2503.07877","title":"Cost-Aware Optimal Pairwise Pure Exploration","created":"2025-03-10","cited_by_count":0,"area":null},{"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":"2506.21834","title":"PrefPaint: Enhancing Medical Image Inpainting through Expert Human Feedback","created":"2025-06-27","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":"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":"2602.19041","title":"Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2603.00567","title":"Learning to Attack: A Bandit Approach to Adversarial Context Poisoning","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2603.01171","title":"PARWiS: Winner determination under shoestring budgets using active pairwise comparisons","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2603.18972","title":"Best-of-Both-Worlds Multi-Dueling Bandits: Unified Algorithms for Stochastic and Adversarial Preferences under Condorcet and Borda Objectives","created":"2026-03-19","cited_by_count":0,"area":null},{"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":"2605.01752","title":"Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial Corruptions","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2606.00846","title":"CUPID in the Model Zoo: Online Matchmaking for Selecting Your Dream LLM","created":"2026-05-30","cited_by_count":0,"area":null},{"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}],"next_cursor":"100"}