{"total":17,"rows":[{"id":"2502.18770","title":"Reward Shaping to Mitigate Reward Hacking in RLHF","created":"2025-02-26","cited_by_count":88,"area":"alignment"},{"id":"2501.09620","title":"Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment","created":"2025-01-16","cited_by_count":42,"area":"alignment"},{"id":"2504.10045","title":"CHARM: Calibrating Reward Models With Chatbot Arena Scores","created":"2025-04-14","cited_by_count":7,"area":"alignment"},{"id":"2505.12843","title":"Bias Fitting to Mitigate Length Bias of Reward Model in RLHF","created":"2025-05-19","cited_by_count":7,"area":"alignment"},{"id":"2512.23461","title":"Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance","created":"2025-12-29","cited_by_count":7,"area":"alignment"},{"id":"2603.10535","title":"Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning","created":"2026-03-11","cited_by_count":7,"area":"alignment"},{"id":"2511.12573","title":"Mitigating Length Bias in RLHF through a Causal Lens","created":"2025-11-16","cited_by_count":6,"area":"alignment"},{"id":"2504.13134","title":"Energy-Based Reward Models for Robust Language Model Alignment","created":"2025-04-17","cited_by_count":4,"area":"alignment"},{"id":"2606.17006","title":"TuneJury: An Open Metric for Improving Music Generation Preference Alignment","created":"2026-06-15","cited_by_count":4,"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":"2603.12795","title":"SteerRM: Debiasing Reward Models via Sparse Autoencoders","created":"2026-03-13","cited_by_count":2,"area":"alignment"},{"id":"2508.07638","title":"Data Selection for LLM Alignment Using Fine-Grained Preferences","created":"2025-08-11","cited_by_count":1,"area":"alignment"},{"id":"2512.06343","title":"When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models","created":"2025-12-06","cited_by_count":1,"area":"alignment"},{"id":"2604.27495","title":"Debiasing Reward Models via Causally Motivated Inference-Time Intervention","created":"2026-04-30","cited_by_count":0,"area":"alignment"},{"id":"2605.30487","title":"Configurable Reward Model for Balanced Safety Alignment","created":"2026-05-28","cited_by_count":0,"area":"alignment"},{"id":"2606.07988","title":"PAFO: Pareto Fairness Optimization for Personalized Reward Modeling","created":"2026-06-06","cited_by_count":0,"area":"alignment"},{"id":"2607.24484","title":"What do Reward Models Memorize?","created":"2026-07-27","cited_by_count":0,"area":"alignment"}],"next_cursor":null}