{"total":22,"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":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"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":"2408.16984","title":"Beyond Preferences in AI Alignment","created":"2024-08-30","cited_by_count":49,"area":"alignment"},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2310.11971","title":"Improving Generalization of Alignment with Human Preferences through Group Invariant Learning","created":"2023-10-18","cited_by_count":25,"area":"alignment"},{"id":"2402.10184","title":"Reward Generalization in RLHF: A Topological Perspective","created":"2024-02-15","cited_by_count":9,"area":"alignment"},{"id":"2410.23953","title":"Representative Social Choice: From Learning Theory to AI Alignment","created":"2024-10-31","cited_by_count":8,"area":"alignment"},{"id":"2406.18777","title":"Aligning Model Properties via Conformal Risk Control","created":"2024-06-26","cited_by_count":7,"area":"alignment"},{"id":"2505.10597","title":"Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment","created":"2025-05-15","cited_by_count":6,"area":"alignment"},{"id":"2511.02109","title":"Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferences","created":"2025-11-03","cited_by_count":6,"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":"2506.05070","title":"RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation","created":"2025-06-05","cited_by_count":4,"area":"alignment"},{"id":"2603.09400","title":"Reward Prediction with Factorized World States","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2604.12086","title":"Robust Optimization for Mitigating Reward Hacking with Correlated Proxies","created":"2026-04-13","cited_by_count":2,"area":"alignment"},{"id":"2404.12150","title":"Aligning language models with human preferences","created":"2024-04-18","cited_by_count":1,"area":"alignment"},{"id":"2407.16025","title":"Exploring and Addressing Reward Confusion in Offline Preference Learning","created":"2024-07-22","cited_by_count":1,"area":"alignment"},{"id":"2408.08995","title":"On the Undecidability of Artificial Intelligence Alignment: Machines that Halt","created":"2024-08-16","cited_by_count":1,"area":"alignment"},{"id":"2601.21350","title":"Factored Causal Representation Learning for Robust Reward Modeling in RLHF","created":"2026-01-29","cited_by_count":1,"area":"alignment"},{"id":"2604.26360","title":"Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking","created":"2026-04-29","cited_by_count":1,"area":"alignment"},{"id":"2508.06592","title":"Towards Integrated Alignment","created":"2025-08-08","cited_by_count":0,"area":"alignment"},{"id":"2603.29993","title":"Extending MONA in Camera Dropbox: Reproduction, Learned Approval, and Design Implications for Reward-Hacking Mitigation","created":"2026-03-31","cited_by_count":0,"area":"alignment"}],"next_cursor":null}