{"total":20,"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":"2205.12401","title":"Reward Uncertainty for Exploration in Preference-based Reinforcement Learning","created":"2022-05-24","cited_by_count":61,"area":"alignment"},{"id":"2204.06601","title":"Causal Confusion and Reward Misidentification in Preference-Based Reward Learning","created":"2022-04-13","cited_by_count":53,"area":"alignment"},{"id":"2403.03185","title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking","created":"2024-03-05","cited_by_count":50,"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":"2301.03652","title":"On The Fragility of Learned Reward Functions","created":"2023-01-09","cited_by_count":21,"area":"alignment"},{"id":"2210.09151","title":"Symbol Guided Hindsight Priors for Reward Learning from Human Preferences","created":"2022-10-17","cited_by_count":8,"area":"alignment"},{"id":"2203.13553","title":"Preprocessing Reward Functions for Interpretability","created":"2022-03-25","cited_by_count":7,"area":"alignment"},{"id":"2406.15753","title":"The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret","created":"2024-06-22","cited_by_count":6,"area":"alignment"},{"id":"2310.08164","title":"Interpreting Learned Feedback Patterns in Large Language Models","created":"2023-10-12","cited_by_count":4,"area":"alignment"},{"id":"2504.10002","title":"FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions","created":"2025-04-14","cited_by_count":3,"area":"alignment"},{"id":"2510.18913","title":"ADPO: Anchored Direct Preference Optimization","created":"2025-10-21","cited_by_count":3,"area":"alignment"},{"id":"2210.01007","title":"Reward Learning with Trees: Methods and Evaluation","created":"2022-10-03","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":"2603.09400","title":"Reward Prediction with Factorized World States","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2305.16924","title":"Learning Interpretable Models of Aircraft Handling Behaviour by Reinforcement Learning from Human Feedback","created":"2023-05-26","cited_by_count":0,"area":"alignment"},{"id":"2306.13004","title":"Can Differentiable Decision Trees Enable Interpretable Reward Learning from Human Feedback?","created":"2023-06-22","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":"2606.09124","title":"A Regret Minimization Framework on Preference Learning in Large Language Models","created":"2026-06-08","cited_by_count":0,"area":"alignment"},{"id":"2608.03875","title":"Enhancing VLM Reward Models Through Structure-Aware Fine-Tuning","created":"2026-08-04","cited_by_count":0,"area":"alignment"}],"next_cursor":null}