{"total":32,"rows":[{"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":"2506.03637","title":"RewardAnything: Generalizable Principle-Following Reward Models","created":"2025-06-04","cited_by_count":28,"area":"alignment"},{"id":"2605.12474","title":"Reward Hacking in Rubric-Based Reinforcement Learning","created":"2026-05-12","cited_by_count":26,"area":"alignment"},{"id":"2606.04923","title":"Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning","created":"2026-06-03","cited_by_count":16,"area":"alignment"},{"id":"2506.01183","title":"Doubly Robust Alignment for Large Language Models","created":"2025-06-01","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":"2509.19333","title":"Pluralistic Off-policy Evaluation and Alignment","created":"2025-09-15","cited_by_count":11,"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":"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":"2606.19818","title":"Uncertainty-Aware Reward Modeling for Stable RLHF","created":"2026-06-18","cited_by_count":6,"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":"2604.16242","title":"Detecting and Suppressing Reward Hacking with Gradient Fingerprints","created":"2026-04-17","cited_by_count":5,"area":"alignment"},{"id":"2605.04266","title":"Explaining and Preventing Alignment Collapse in Iterative RLHF","created":"2026-05-05","cited_by_count":4,"area":"alignment"},{"id":"2511.17879","title":"Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction","created":"2025-11-22","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":"2605.06036","title":"Optimal Transport for LLM Reward Modeling from Noisy Preference","created":"2026-05-07","cited_by_count":3,"area":"alignment"},{"id":"2504.16272","title":"Learning Explainable Dense Reward Shapes via Bayesian Optimization","created":"2025-04-22","cited_by_count":2,"area":"alignment"},{"id":"2602.02572","title":"Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective","created":"2026-01-31","cited_by_count":2,"area":"alignment"},{"id":"2602.09653","title":"ClinAlign: Scaling Healthcare Alignment from Clinician Preference","created":"2026-02-10","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":"2503.22480","title":"Probabilistic Uncertain Reward Model","created":"2025-03-28","cited_by_count":1,"area":"alignment"},{"id":"2509.14659","title":"Aligning Audio Captions with Human Preferences","created":"2025-09-18","cited_by_count":1,"area":"alignment"},{"id":"2510.13036","title":"Repairing Reward Functions with Feedback to Mitigate Reward Hacking","created":"2025-10-14","cited_by_count":1,"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":"2605.18721","title":"General Preference Reinforcement Learning","created":"2026-05-18","cited_by_count":1,"area":"alignment"},{"id":"2606.28294","title":"Democratic ICAI: Debating Our Way to Steering Principles from Preferences","created":"2026-06-26","cited_by_count":1,"area":"alignment"},{"id":"2508.09155","title":"A Rolling Stone Gathers No Moss: Adaptive Policy Optimization for Stable Self-Evaluation in Large Multimodal Models","created":"2025-08-05","cited_by_count":0,"area":"alignment"},{"id":"2509.24713","title":"Circuit-Aware Reward Training: A Mechanistic Framework for Longtail Robustness in RLHF","created":"2025-09-29","cited_by_count":0,"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":"2605.11865","title":"Variance-aware Reward Modeling with Anchor Guidance","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2606.10528","title":"Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output","created":"2026-06-09","cited_by_count":0,"area":"alignment"}],"next_cursor":null}