{"total":20,"rows":[{"id":"2407.04549","title":"Spontaneous Reward Hacking in Iterative Self-Refinement","created":"2024-07-05","cited_by_count":26,"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":"2404.10160","title":"Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs","created":"2024-04-15","cited_by_count":22,"area":"alignment"},{"id":"2512.16626","title":"Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game","created":"2025-12-18","cited_by_count":10,"area":"alignment"},{"id":"2406.07168","title":"Teaching Language Models to Self-Improve by Learning from Language Feedback","created":"2024-06-11","cited_by_count":9,"area":"alignment"},{"id":"2410.11055","title":"Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only","created":"2024-10-14","cited_by_count":9,"area":"alignment"},{"id":"2502.05478","title":"OntoTune: Ontology-Driven Self-training for Aligning Large Language Models","created":"2025-02-08","cited_by_count":8,"area":"alignment"},{"id":"2502.13417","title":"RLTHF: Targeted Human Feedback for LLM Alignment","created":"2025-02-19","cited_by_count":8,"area":"alignment"},{"id":"2410.01735","title":"LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits","created":"2024-10-02","cited_by_count":7,"area":"alignment"},{"id":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"id":"2603.00025","title":"TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation","created":"2026-02-03","cited_by_count":7,"area":"alignment"},{"id":"2502.04675","title":"Scalable Oversight for Superhuman AI via Recursive Self-Critiquing","created":"2025-02-07","cited_by_count":4,"area":"alignment"},{"id":"2608.17776","title":"Debate Training Reduces Reward Hacking in RLAIF","created":"2026-08-18","cited_by_count":4,"area":"alignment"},{"id":"2311.07587","title":"Frontier Language Models are not Robust to Adversarial Arithmetic, or \"What do I need to say so you agree 2+2=5?","created":"2023-11-08","cited_by_count":3,"area":"alignment"},{"id":"2604.17501","title":"CoAct: Co-Active LLM Preference Learning with Human-AI Synergy","created":"2026-04-19","cited_by_count":3,"area":"alignment"},{"id":"2506.00396","title":"Speculative Reward Model Boosts Decision Making Ability of LLMs Cost-Effectively","created":"2025-05-31","cited_by_count":0,"area":"alignment"},{"id":"2509.24781","title":"SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models","created":"2025-09-29","cited_by_count":0,"area":"alignment"},{"id":"2609.01597","title":"The Rise of Verbal Reinforcement Learning","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.32617","title":"The Alignment Paradox: How Post-Training Amplifies Confident Hallucinations in Language Models","created":"2026-09-26","cited_by_count":0,"area":"alignment"},{"id":"2610.20350","title":"Lifted State Policy Optimization: Internalizing Self-Correction through Transition Geometry","created":"2026-10-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}