{"total":43,"rows":[{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2502.18770","title":"Reward Shaping to Mitigate Reward Hacking in RLHF","created":"2025-02-26","cited_by_count":88,"area":"alignment"},{"id":"2506.19248","title":"Inference-Time Reward Hacking in Large Language Models","created":"2025-06-24","cited_by_count":34,"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":"2501.19358","title":"The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking","created":"2025-01-31","cited_by_count":18,"area":"alignment"},{"id":"2507.05197","title":"Pre-Trained Policy Discriminators are General Reward Models","created":"2025-07-07","cited_by_count":15,"area":"alignment"},{"id":"2505.18126","title":"Reward Model Overoptimisation in Iterated RLHF","created":"2025-05-23","cited_by_count":12,"area":"alignment"},{"id":"2507.07375","title":"Bradley-Terry and Multi-Objective Reward Modeling Are Complementary","created":"2025-07-10","cited_by_count":11,"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":"2603.08091","title":"Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization","created":"2026-03-09","cited_by_count":9,"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":"2603.18736","title":"CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks","created":"2026-03-19","cited_by_count":7,"area":"alignment"},{"id":"2505.10597","title":"Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment","created":"2025-05-15","cited_by_count":6,"area":"alignment"},{"id":"2507.00665","title":"SAFER: Probing Safety in Reward Models with Sparse Autoencoder","created":"2025-07-01","cited_by_count":6,"area":"alignment"},{"id":"2603.15646","title":"Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy","created":"2026-03-04","cited_by_count":6,"area":"alignment"},{"id":"2606.19818","title":"Uncertainty-Aware Reward Modeling for Stable RLHF","created":"2026-06-18","cited_by_count":6,"area":"alignment"},{"id":"2505.17122","title":"Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?","created":"2025-05-21","cited_by_count":5,"area":"alignment"},{"id":"2505.23316","title":"Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO","created":"2025-05-29","cited_by_count":5,"area":"alignment"},{"id":"2508.02618","title":"Alleviating Attention Hacking in Discriminative Reward Modeling through Interaction Distillation","created":"2025-08-04","cited_by_count":5,"area":"alignment"},{"id":"2510.13694","title":"Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking","created":"2025-10-15","cited_by_count":5,"area":"alignment"},{"id":"2602.10623","title":"Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling","created":"2026-02-11","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":"2510.13212","title":"Towards Understanding Valuable Preference Data for Large Language Model Alignment","created":"2025-10-15","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":"2603.23184","title":"ImplicitRM: Unbiased Reward Modeling from Implicit Preference Data for LLM alignment","created":"2026-03-24","cited_by_count":3,"area":"alignment"},{"id":"2605.06036","title":"Optimal Transport for LLM Reward Modeling from Noisy Preference","created":"2026-05-07","cited_by_count":3,"area":"alignment"},{"id":"2606.21795","title":"Discretizing Reward Models","created":"2026-06-19","cited_by_count":3,"area":"alignment"},{"id":"2608.27505","title":"A Survey on Rubric-Guided Reinforcement Learning for Language Models","created":"2026-08-27","cited_by_count":3,"area":"alignment"},{"id":"2506.03234","title":"BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF","created":"2025-06-03","cited_by_count":2,"area":"alignment"},{"id":"2506.04272","title":"Understanding the Impact of Sampling Quality in Direct Preference Optimization","created":"2025-06-03","cited_by_count":2,"area":"alignment"},{"id":"2509.23564","title":"Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment","created":"2025-09-28","cited_by_count":2,"area":"alignment"},{"id":"2609.00213","title":"Uncovering and Mitigating Aggregation-Induced Reward Hacking in Multi-Reward Reinforcement Learning","created":"2026-08-31","cited_by_count":2,"area":"alignment"},{"id":"2601.21350","title":"Factored Causal Representation Learning for Robust Reward Modeling in RLHF","created":"2026-01-29","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":"2610.05308","title":"RubricArmor: Adversarial Evolution Improves LLM-Based Rubric Generation","created":"2026-10-04","cited_by_count":1,"area":"alignment"},{"id":"2511.23092","title":"Does Self-Evaluation Enable Wireheading in Language Models?","created":"2025-11-28","cited_by_count":0,"area":"alignment"},{"id":"2512.00724","title":"UMM-RM: An Upcycle-and-Merge MoE Reward Model for Mitigating Reward Hacking","created":"2025-11-30","cited_by_count":0,"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":"2605.00155","title":"Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback","created":"2026-04-30","cited_by_count":0,"area":"alignment"},{"id":"2605.27355","title":"Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases","created":"2026-05-26","cited_by_count":0,"area":"alignment"},{"id":"2607.18258","title":"S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF","created":"2026-05-15","cited_by_count":0,"area":"alignment"},{"id":"2609.33221","title":"RMB: Reward Model Boosting Mitigates Reward Hacking","created":"2026-09-27","cited_by_count":0,"area":"alignment"}],"next_cursor":null}