{"total":54,"rows":[{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2404.12358","title":"From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function","created":"2024-04-18","cited_by_count":242,"area":"alignment"},{"id":"2401.06080","title":"Secrets of RLHF in Large Language Models Part II: Reward Modeling","created":"2024-01-11","cited_by_count":171,"area":"alignment"},{"id":"2404.11999","title":"Token-level Direct Preference Optimization","created":"2024-04-18","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":"2410.09724","title":"Taming Overconfidence in LLMs: Reward Calibration in RLHF","created":"2024-10-13","cited_by_count":112,"area":"alignment"},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2303.00957","title":"Preference Transformer: Modeling Human Preferences using Transformers for RL","created":"2023-03-02","cited_by_count":79,"area":null},{"id":"2310.13639","title":"Contrastive Preference Learning: Learning from Human Feedback without RL","created":"2023-10-20","cited_by_count":79,"area":"alignment"},{"id":"2407.04842","title":"MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?","created":"2024-07-05","cited_by_count":66,"area":"diffusion"},{"id":"2310.12962","title":"An Emulator for Fine-Tuning Large Language Models using Small Language Models","created":"2023-10-19","cited_by_count":61,"area":null},{"id":"2402.08265","title":"A Dense Reward View on Aligning Text-to-Image Diffusion with Preference","created":"2024-02-13","cited_by_count":55,"area":"diffusion"},{"id":"2410.08193","title":"GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment","created":"2024-10-10","cited_by_count":54,"area":"alignment"},{"id":"2305.16217","title":"Beyond Reward: Offline Preference-guided Policy Optimization","created":"2023-05-25","cited_by_count":35,"area":"alignment"},{"id":"2506.15421","title":"Reward Models in Deep Reinforcement Learning: A Survey","created":"2025-06-18","cited_by_count":25,"area":"alignment"},{"id":"2503.18991","title":"Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment","created":"2025-03-23","cited_by_count":20,"area":"alignment"},{"id":"2310.02456","title":"Learning Optimal Advantage from Preferences and Mistaking it for Reward","created":"2023-10-03","cited_by_count":19,"area":"alignment"},{"id":"2507.13541","title":"PrefPalette: Personalized Preference Modeling with Latent Attributes","created":"2025-07-17","cited_by_count":16,"area":null},{"id":"2207.02442","title":"Transformers are Adaptable Task Planners","created":"2022-07-06","cited_by_count":15,"area":null},{"id":"2409.05622","title":"Forward KL Regularized Preference Optimization for Aligning Diffusion Policies","created":"2024-09-09","cited_by_count":10,"area":"diffusion"},{"id":"2407.16008","title":"Boosting Reward Model with Preference-Conditional Multi-Aspect Synthetic Data Generation","created":"2024-07-22","cited_by_count":9,"area":"alignment"},{"id":"2409.00162","title":"Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback","created":"2024-08-30","cited_by_count":9,"area":"alignment"},{"id":"2502.21038","title":"Reward Learning from Multiple Feedback Types","created":"2025-02-28","cited_by_count":9,"area":"agents"},{"id":"2406.15599","title":"Pareto-Optimal Learning from Preferences with Hidden Context","created":"2024-06-21","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":"2405.00746","title":"Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning","created":"2024-04-30","cited_by_count":6,"area":"deeprl"},{"id":"2502.15210","title":"PairBench: Are Vision-Language Models Reliable at Comparing What They See?","created":"2025-02-21","cited_by_count":6,"area":"mllm"},{"id":"2407.04185","title":"HAF-RM: A Hybrid Alignment Framework for Reward Model Training","created":"2024-07-04","cited_by_count":5,"area":"alignment"},{"id":"2501.06416","title":"Influencing Humans to Conform to Preference Models for RLHF","created":"2025-01-11","cited_by_count":4,"area":"alignment"},{"id":"2505.22998","title":"LLM Agents for Bargaining with Utility-based Feedback","created":"2025-05-29","cited_by_count":4,"area":"agents"},{"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":"2407.04451","title":"Hindsight Preference Learning for Offline Preference-based Reinforcement Learning","created":"2024-07-05","cited_by_count":3,"area":null},{"id":"2310.15694","title":"COPR: Continual Learning Human Preference through Optimal Policy Regularization","created":"2023-10-24","cited_by_count":2,"area":"alignment"},{"id":"2504.15472","title":"LAPP: Large Language Model Feedback for Preference-Driven Reinforcement Learning","created":"2025-04-21","cited_by_count":2,"area":"alignment"},{"id":"2505.06273","title":"Policy-labeled Preference Learning: Is Preference Enough for RLHF?","created":"2025-05-06","cited_by_count":2,"area":"alignment"},{"id":"2507.10995","title":"Misalignment from Treating Means as Ends","created":"2025-07-15","cited_by_count":2,"area":null},{"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":"2602.10467","title":"MERIT Feedback Elicits Better Bargaining in LLM Negotiators","created":"2026-02-11","cited_by_count":2,"area":"alignment"},{"id":"2606.21550","title":"AI Alignment From Social Choice Perspectives","created":"2026-06-19","cited_by_count":2,"area":"alignment"},{"id":"2412.10529","title":"Solving the Inverse Alignment Problem for Efficient RLHF","created":"2024-12-13","cited_by_count":1,"area":"alignment"},{"id":"2503.00930","title":"Behavior Preference Regression for Offline Reinforcement Learning","created":"2025-03-02","cited_by_count":1,"area":"alignment"},{"id":"2503.18347","title":"Latent Embedding Adaptation for Human Preference Alignment in Diffusion Planners","created":"2025-03-24","cited_by_count":1,"area":"alignment"},{"id":"2510.13036","title":"Repairing Reward Functions with Feedback to Mitigate Reward Hacking","created":"2025-10-14","cited_by_count":1,"area":"alignment"},{"id":"2512.20173","title":"Offline Safe Policy Optimization From Heterogeneous Feedback","created":"2025-12-23","cited_by_count":1,"area":"alignment"},{"id":"2410.22690","title":"Choice Between Partial Trajectories: Disentangling Goals from Beliefs","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2503.07848","title":"Safe Explicable Policy Search","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2505.06284","title":"DMRL: Data- and Model-aware Reward Learning for Data Extraction","created":"2025-05-07","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":"2601.16906","title":"The Trajectory Alignment Coefficient in Two Acts: From Reward Tuning to Reward Learning","created":"2026-01-23","cited_by_count":0,"area":"alignment"},{"id":"2605.21822","title":"Implicit Safety Alignment from Crowd Preferences","created":"2026-05-20","cited_by_count":0,"area":"alignment"},{"id":"2606.11982","title":"PAWS: Preference Learning with Advantage-Weighted Segments","created":"2026-06-10","cited_by_count":0,"area":"deeprl"},{"id":"2606.12603","title":"From Imitation to Alignment: Human-Preference Flow Policies for Long-Horizon Sidewalk Navigation","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2608.02951","title":"SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling","created":"2026-08-03","cited_by_count":0,"area":"alignment"},{"id":"2609.15544","title":"Specifying Reward Functions for RL Without Environment Sampling","created":"2026-09-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}