{"total":36,"rows":[{"id":"2502.18770","title":"Reward Shaping to Mitigate Reward Hacking in RLHF","created":"2025-02-26","cited_by_count":88,"area":"alignment"},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"area":"alignment"},{"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":"2504.14716","title":"Pairwise or Pointwise? Evaluating Feedback Protocols for Bias in LLM-Based Evaluation","created":"2025-04-20","cited_by_count":24,"area":"alignment"},{"id":"2501.13011","title":"MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking","created":"2025-01-22","cited_by_count":19,"area":"alignment"},{"id":"2501.08617","title":"RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation","created":"2025-01-15","cited_by_count":15,"area":"alignment"},{"id":"2602.01750","title":"Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking","created":"2026-02-02","cited_by_count":11,"area":"alignment"},{"id":"2607.05904","title":"More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges","created":"2026-07-07","cited_by_count":10,"area":"alignment"},{"id":"2509.23102","title":"Multiplayer Nash Preference Optimization","created":"2025-09-27","cited_by_count":7,"area":"alignment"},{"id":"2506.07165","title":"AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models","created":"2025-06-08","cited_by_count":6,"area":"alignment"},{"id":"2509.18632","title":"A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users","created":"2025-09-23","cited_by_count":6,"area":"alignment"},{"id":"2411.10156","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","created":"2024-11-15","cited_by_count":5,"area":"alignment"},{"id":"2501.07886","title":"Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision","created":"2025-01-14","cited_by_count":5,"area":"alignment"},{"id":"2509.05381","title":"Murphys Laws of AI Alignment: Why the Gap Always Wins","created":"2025-09-04","cited_by_count":5,"area":"alignment"},{"id":"2602.19416","title":"IR$^3$: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking","created":"2026-02-23","cited_by_count":5,"area":"alignment"},{"id":"2604.16242","title":"Detecting and Suppressing Reward Hacking with Gradient Fingerprints","created":"2026-04-17","cited_by_count":5,"area":"alignment"},{"id":"2602.11523","title":"Unifying Stable Optimization and Reference Regularization in RLHF","created":"2026-02-12","cited_by_count":4,"area":"alignment"},{"id":"2602.15222","title":"Automatically Finding Reward Model Biases","created":"2026-02-16","cited_by_count":4,"area":"alignment"},{"id":"2604.02507","title":"Reinforcement Learning from Human Feedback: A Statistical Perspective","created":"2026-04-02","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":"2503.04249","title":"How to Mitigate Overfitting in Weak-to-strong Generalization?","created":"2025-03-06","cited_by_count":3,"area":"alignment"},{"id":"2603.03291","title":"One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models","created":"2026-02-06","cited_by_count":3,"area":"alignment"},{"id":"2604.02686","title":"Beyond Semantic Manipulation: Token-Space Attacks on Reward Models","created":"2026-04-03","cited_by_count":3,"area":"alignment"},{"id":"2607.01830","title":"Many Voices, One Reward: Multi-Role Rubric Generation for LLM Judging and Reward Modeling","created":"2026-07-02","cited_by_count":3,"area":"alignment"},{"id":"2503.17965","title":"Understanding the Effects of RLHF on the Quality and Detectability of LLM-Generated Texts","created":"2025-03-23","cited_by_count":2,"area":"alignment"},{"id":"2507.02850","title":"LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users","created":"2025-07-03","cited_by_count":2,"area":"alignment"},{"id":"2510.03231","title":"Reward Models are Metrics in a Trench Coat","created":"2025-10-03","cited_by_count":2,"area":"alignment"},{"id":"2606.09043","title":"DynaCF: Mitigating Shortcut Learning in Reward Models via Dynamic Counterfactual Sensitivity","created":"2026-06-08","cited_by_count":2,"area":"alignment"},{"id":"2512.05464","title":"Dynamic Alignment for Collective Agency: Toward a Scalable Self-Improving Framework for Open-Ended LLM Alignment","created":"2025-12-05","cited_by_count":1,"area":"alignment"},{"id":"2606.09711","title":"Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization","created":"2026-06-08","cited_by_count":1,"area":"alignment"},{"id":"2607.02291","title":"Optimizing Visual Generative Models via Distribution-wise Rewards","created":"2026-07-02","cited_by_count":1,"area":"alignment"},{"id":"2509.05605","title":"Icon$^{2}$: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation","created":"2025-09-06","cited_by_count":0,"area":"alignment"},{"id":"2602.15338","title":"Discovering Implicit Large Language Model Alignment Objectives","created":"2026-02-17","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":"2605.04356","title":"Efficiently Aligning Language Models with Online Natural Language Feedback","created":"2026-05-05","cited_by_count":0,"area":"alignment"},{"id":"2610.12822","title":"Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems","created":"2026-10-09","cited_by_count":0,"area":"alignment"}],"next_cursor":null}