{"total":15,"rows":[{"id":"2510.17314","title":"Auto-Rubric: Learning From Implicit Weights to Explicit Rubrics for Reward Modeling","created":"2025-10-20","cited_by_count":30,"area":"alignment"},{"id":"2503.15484","title":"Value Profiles for Encoding Human Variation","created":"2025-03-19","cited_by_count":29,"area":"alignment"},{"id":"2510.26202","title":"What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data","created":"2025-10-30","cited_by_count":26,"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":"2501.17112","title":"Decoding Human Preferences in Alignment: An Improved Approach to Inverse Constitutional AI","created":"2025-01-28","cited_by_count":4,"area":"alignment"},{"id":"2608.27505","title":"A Survey on Rubric-Guided Reinforcement Learning for Language Models","created":"2026-08-27","cited_by_count":3,"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":"2606.28294","title":"Democratic ICAI: Debating Our Way to Steering Principles from Preferences","created":"2026-06-26","cited_by_count":1,"area":"alignment"},{"id":"2509.26305","title":"Feedback Forensics: A Toolkit to Measure AI Personality","created":"2025-09-30","cited_by_count":0,"area":"alignment"},{"id":"2511.02623","title":"The Realignment Problem: When Right becomes Wrong in LLMs","created":"2025-11-04","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":"2605.19665","title":"CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging","created":"2026-05-19","cited_by_count":0,"area":"alignment"},{"id":"2606.24004","title":"Towards Spec Learning: Inference-Time Alignment from Preference Pairs","created":"2026-06-22","cited_by_count":0,"area":"alignment"},{"id":"2606.30116","title":"Open Problems in Constitutional Preference Reconstruction","created":"2026-06-29","cited_by_count":0,"area":"alignment"},{"id":"2608.28593","title":"Statutory AI: Aligning Large Language Models With Legal Norms","created":"2026-06-13","cited_by_count":0,"area":"alignment"}],"next_cursor":null}