{"total":17,"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":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2408.16984","title":"Beyond Preferences in AI Alignment","created":"2024-08-30","cited_by_count":49,"area":"alignment"},{"id":"2405.17713","title":"AI Alignment with Changing and Influenceable Reward Functions","created":"2024-05-28","cited_by_count":33,"area":"alignment"},{"id":"2208.10687","title":"The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types","created":"2022-08-23","cited_by_count":26,"area":"alignment"},{"id":"2310.13011","title":"Compositional preference models for aligning LMs","created":"2023-10-17","cited_by_count":26,"area":"alignment"},{"id":"2201.00012","title":"MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learning","created":"2021-12-30","cited_by_count":25,"area":"alignment"},{"id":"2405.15065","title":"Direct Preference Optimization With Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences","created":"2024-05-23","cited_by_count":23,"area":"alignment"},{"id":"2402.02423","title":"Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback","created":"2024-02-04","cited_by_count":21,"area":"alignment"},{"id":"2308.04332","title":"RLHF-Blender: A Configurable Interactive Interface for Learning from Diverse Human Feedback","created":"2023-08-08","cited_by_count":15,"area":"alignment"},{"id":"2406.01013","title":"Scalable Ensembling For Mitigating Reward Overoptimisation","created":"2024-06-03","cited_by_count":14,"area":"alignment"},{"id":"2303.00894","title":"Active Reward Learning from Multiple Teachers","created":"2023-03-02","cited_by_count":13,"area":"alignment"},{"id":"2401.14923","title":"Reinforcement Learning Interventions on Boundedly Rational Human Agents in Frictionful Tasks","created":"2024-01-26","cited_by_count":2,"area":"alignment"},{"id":"2510.15716","title":"Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences","created":"2025-10-17","cited_by_count":1,"area":"alignment"},{"id":"2607.00001","title":"Constructive Alignment: Governing Preference Dynamics in Human-AI Interaction","created":"2026-04-01","cited_by_count":1,"area":"alignment"},{"id":"2607.04590","title":"Attention Limited Reward Learning","created":"2026-07-06","cited_by_count":1,"area":"alignment"},{"id":"2605.06895","title":"Mitigating Cognitive Bias in RLHF by Altering Rationality","created":"2026-05-07","cited_by_count":0,"area":"alignment"}],"next_cursor":null}