{"total":20,"rows":[{"id":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360,"area":"alignment"},{"id":"2401.06080","title":"Secrets of RLHF in Large Language Models Part II: Reward Modeling","created":"2024-01-11","cited_by_count":171,"area":"alignment"},{"id":"2410.12832","title":"Generative Reward Models","created":"2024-10-02","cited_by_count":148,"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":"2511.18397","title":"Natural Emergent Misalignment from Reward Hacking in Production RL","created":"2025-11-23","cited_by_count":136,"area":"alignment"},{"id":"2411.01111","title":"Rule Based Rewards for Language Model Safety","created":"2024-11-02","cited_by_count":108,"area":"alignment"},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2406.06560","title":"Inverse Constitutional AI: Compressing Preferences into Principles","created":"2024-06-02","cited_by_count":41,"area":"alignment"},{"id":"2506.08123","title":"QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA","created":"2025-06-09","cited_by_count":28,"area":"alignment"},{"id":"2401.11458","title":"Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback","created":"2024-01-21","cited_by_count":25,"area":"alignment"},{"id":"2511.01689","title":"Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI","created":"2025-11-03","cited_by_count":24,"area":"alignment"},{"id":"2404.14313","title":"Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels","created":"2024-04-22","cited_by_count":19,"area":"alignment"},{"id":"2507.05197","title":"Pre-Trained Policy Discriminators are General Reward Models","created":"2025-07-07","cited_by_count":15,"area":"alignment"},{"id":"2410.12999","title":"POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization","created":"2024-10-16","cited_by_count":8,"area":"alignment"},{"id":"2501.15453","title":"Data-adaptive Safety Rules for Training Reward Models","created":"2025-01-26","cited_by_count":6,"area":"alignment"},{"id":"2503.20995","title":"ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models","created":"2025-03-26","cited_by_count":4,"area":"alignment"},{"id":"2606.24014","title":"Reinforcement Learning Towards Broadly and Persistently Beneficial Models","created":"2026-06-22","cited_by_count":4,"area":"alignment"},{"id":"2406.11190","title":"Aligning Large Language Models from Self-Reference AI Feedback with one General Principle","created":"2024-06-17","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":"2610.07935","title":"SIGMA: Self-Improving Alignment Generalization from a Model Spec","created":"2026-10-06","cited_by_count":0,"area":"alignment"}],"next_cursor":null}