{"total":17,"rows":[{"id":"2312.14925","title":"A Survey of Reinforcement Learning from Human Feedback","created":"2023-12-22","cited_by_count":264,"area":"alignment"},{"id":"2407.10490","title":"Learning Dynamics of LLM Finetuning","created":"2024-07-15","cited_by_count":95,"area":"alignment"},{"id":"2402.06627","title":"Feedback Loops With Language Models Drive In-Context Reward Hacking","created":"2024-02-09","cited_by_count":77,"area":"alignment"},{"id":"2312.07000","title":"Alignment for Honesty","created":"2023-12-12","cited_by_count":74,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2405.13967","title":"Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity","created":"2024-05-22","cited_by_count":35,"area":"alignment"},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"area":"alignment"},{"id":"2310.01045","title":"Tool-Augmented Reward Modeling","created":"2023-10-02","cited_by_count":20,"area":"alignment"},{"id":"2404.03862","title":"Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data","created":"2024-04-05","cited_by_count":13,"area":"alignment"},{"id":"2410.02205","title":"Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language Models","created":"2024-10-03","cited_by_count":12,"area":"alignment"},{"id":"2603.06604","title":"Know When You're Wrong: Aligning Confidence with Correctness for LLM Error Detection","created":"2026-02-18","cited_by_count":8,"area":"alignment"},{"id":"2412.08201","title":"Model-Editing-Based Jailbreak against Safety-aligned Large Language Models","created":"2024-12-11","cited_by_count":4,"area":"alignment"},{"id":"2406.01931","title":"Dishonesty in Helpful and Harmless Alignment","created":"2024-06-04","cited_by_count":3,"area":"alignment"},{"id":"2510.14400","title":"MedTrust-RAG: Evidence Verification and Trust Alignment for Biomedical Question Answering","created":"2025-10-16","cited_by_count":2,"area":"alignment"},{"id":"2605.01507","title":"MILD: Mediator Agent System with Bidirectional Perception and Multi-Layered Alignment for Human-Vehicle Collaboration","created":"2026-05-02","cited_by_count":2,"area":"alignment"},{"id":"2506.12382","title":"Exploring the Secondary Risks of Large Language Models","created":"2025-06-14","cited_by_count":1,"area":"alignment"},{"id":"2602.22146","title":"Provable Last-Iterate Convergence for Multi-Objective Safe LLM Alignment via Optimistic Primal-Dual","created":"2026-02-25","cited_by_count":0,"area":"alignment"}],"next_cursor":null}