{"total":26,"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":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184,"area":"alignment"},{"id":"2406.07814","title":"Collective Constitutional AI: Aligning a Language Model with Public Input","created":"2024-06-12","cited_by_count":123,"area":"alignment"},{"id":"2309.16349","title":"Human Feedback is not Gold Standard","created":"2023-09-28","cited_by_count":83,"area":"alignment"},{"id":"2410.04070","title":"PAD: Personalized Alignment of LLMs at Decoding-Time","created":"2024-10-05","cited_by_count":60,"area":"alignment"},{"id":"2305.00955","title":"Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation","created":"2023-05-01","cited_by_count":55,"area":"alignment"},{"id":"2310.07629","title":"The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values","created":"2023-10-11","cited_by_count":54,"area":"alignment"},{"id":"2408.16984","title":"Beyond Preferences in AI Alignment","created":"2024-08-30","cited_by_count":49,"area":"alignment"},{"id":"2407.02273","title":"Language Model Alignment in Multilingual Trolley Problems","created":"2024-07-02","cited_by_count":46,"area":"alignment"},{"id":"2407.14916","title":"Improving Context-Aware Preference Modeling for Language Models","created":"2024-07-20","cited_by_count":22,"area":"alignment"},{"id":"2507.13383","title":"Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models","created":"2025-07-15","cited_by_count":11,"area":"alignment"},{"id":"2406.15599","title":"Pareto-Optimal Learning from Preferences with Hidden Context","created":"2024-06-21","cited_by_count":8,"area":"alignment"},{"id":"2602.20042","title":"AI Alignment Breaks at the Edge","created":"2026-02-23","cited_by_count":4,"area":"alignment"},{"id":"2406.16807","title":"Beyond Thumbs Up/Down: Untangling Challenges of Fine-Grained Feedback for Text-to-Image Generation","created":"2024-06-24","cited_by_count":3,"area":"alignment"},{"id":"2601.18061","title":"Expert Evaluation and the Limits of Human Feedback in Mental Health AI Safety Testing","created":"2026-01-26","cited_by_count":2,"area":"alignment"},{"id":"2411.10534","title":"Chain of Alignment: Integrating Public Will with Expert Intelligence for Language Model Alignment","created":"2024-11-15","cited_by_count":1,"area":"alignment"},{"id":"2604.03238","title":"RLHF May Not Reflect Genuine Preferences","created":"2026-01-31","cited_by_count":1,"area":"alignment"},{"id":"2505.24199","title":"Intuitionistic Fuzzy Sets for Large Language Model Data Annotation: A Novel Approach to Side-by-Side Preference Labeling","created":"2025-05-30","cited_by_count":0,"area":"alignment"},{"id":"2507.12041","title":"Granular feedback merits sophisticated aggregation","created":"2025-07-16","cited_by_count":0,"area":"alignment"},{"id":"2512.21551","title":"Human-AI Interaction Alignment: Designing, Evaluating, and Evolving Value-Centered AI For Reciprocal Human-AI Futures","created":"2025-12-25","cited_by_count":0,"area":"alignment"},{"id":"2604.25895","title":"Three Models of RLHF Annotation: Extension, Evidence, and Authority","created":"2026-04-28","cited_by_count":0,"area":"alignment"},{"id":"2605.11865","title":"Variance-aware Reward Modeling with Anchor Guidance","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2606.07629","title":"Large Language Models Should Learn Personalized Rather Than Aggregated Human Preferences","created":"2026-05-30","cited_by_count":0,"area":"alignment"},{"id":"2607.16195","title":"Rater State Bias in RLHF Preference Data: An Audit Framework","created":"2026-04-14","cited_by_count":0,"area":"alignment"},{"id":"2607.20515","title":"Reliability-Aware LLM Alignment from Inconsistent Human Feedback","created":"2026-07-07","cited_by_count":0,"area":"alignment"},{"id":"2610.02568","title":"Mitigating Social Sycophancy via Pluralistic Preference Optimization","created":"2026-10-01","cited_by_count":0,"area":"alignment"}],"next_cursor":null}