{"total":22,"rows":[{"id":"2411.02306","title":"On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback","created":"2024-11-04","cited_by_count":47,"area":"alignment"},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2509.03403","title":"Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training","created":"2025-09-03","cited_by_count":29,"area":"alignment"},{"id":"2402.11296","title":"Dissecting Human and LLM Preferences","created":"2024-02-17","cited_by_count":17,"area":"alignment"},{"id":"2603.07084","title":"Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR","created":"2026-03-07","cited_by_count":17,"area":"alignment"},{"id":"2406.18346","title":"AI Alignment through Reinforcement Learning from Human Feedback? Contradictions and Limitations","created":"2024-06-26","cited_by_count":11,"area":"alignment"},{"id":"2602.11180","title":"Mechanistic Interpretability for Large Language Model Alignment: Progress, Challenges, and Future Directions","created":"2026-01-21","cited_by_count":8,"area":"alignment"},{"id":"2506.07523","title":"Aligning What LLMs Do and Say: Towards Self-Consistent Explanations","created":"2025-06-09","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":"2501.06164","title":"Model Alignment Search","created":"2025-01-10","cited_by_count":3,"area":"alignment"},{"id":"2509.13869","title":"Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs","created":"2025-09-17","cited_by_count":3,"area":"alignment"},{"id":"2608.06377","title":"Learning When to Trust via Selective Context Preference Optimization","created":"2026-08-06","cited_by_count":3,"area":"alignment"},{"id":"2609.19101","title":"Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations","created":"2026-09-16","cited_by_count":2,"area":"alignment"},{"id":"2505.13257","title":"Is Active Persona Inference Necessary for Aligning Small Models to Personal Preferences?","created":"2025-05-19","cited_by_count":1,"area":"alignment"},{"id":"2510.07972","title":"SHE: Stepwise Hybrid Examination Reinforcement Learning Framework for E-commerce Search Relevance","created":"2025-10-09","cited_by_count":1,"area":"alignment"},{"id":"2511.21737","title":"Polarity-Aware Probing for Quantifying Latent Alignment in Language Models","created":"2025-11-21","cited_by_count":1,"area":"alignment"},{"id":"2604.26511","title":"Tatemae: Detecting Alignment Faking via Tool Selection in LLMs","created":"2026-04-29","cited_by_count":1,"area":"alignment"},{"id":"2602.05056","title":"Grounded but Misleading: Evaluating Semantic Alignment in AI-Generated Security Explanations","created":"2026-02-04","cited_by_count":0,"area":"alignment"},{"id":"2603.08412","title":"Aligning to Illusions: Choice Blindness in Human and AI Feedback","created":"2026-03-09","cited_by_count":0,"area":"alignment"},{"id":"2608.11493","title":"From Prompting to Behavioral Alignment: Personalized LLM Judges for Recommendation Evaluation","created":"2026-08-11","cited_by_count":0,"area":"alignment"},{"id":"2609.05009","title":"Language models judge war differently when tested for alignment","created":"2026-09-04","cited_by_count":0,"area":"alignment"},{"id":"2610.18766","title":"Rubrics from the Task, Verdicts from Evidence: Pointwise Rubric Rewards with Tool-Augmented Judges","created":"2026-10-13","cited_by_count":0,"area":"alignment"}],"next_cursor":null}