{"total":33,"rows":[{"id":"2409.13156","title":"RRM: Robust Reward Model Training Mitigates Reward Hacking","created":"2024-09-20","cited_by_count":76,"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":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"area":"alignment"},{"id":"2409.17407","title":"Post-hoc Reward Calibration: A Case Study on Length Bias","created":"2024-09-25","cited_by_count":29,"area":"alignment"},{"id":"2510.26202","title":"What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data","created":"2025-10-30","cited_by_count":26,"area":"alignment"},{"id":"2506.16507","title":"Robust Reward Modeling via Causal Rubrics","created":"2025-06-19","cited_by_count":19,"area":"alignment"},{"id":"2505.07271","title":"On the Robustness of Reward Models for Language Model Alignment","created":"2025-05-12","cited_by_count":13,"area":"alignment"},{"id":"2506.05339","title":"Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference Models","created":"2025-06-05","cited_by_count":13,"area":"alignment"},{"id":"2601.22664","title":"Real-Time Aligned Reward Model beyond Semantics","created":"2026-01-30","cited_by_count":13,"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":"2512.23461","title":"Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance","created":"2025-12-29","cited_by_count":7,"area":"alignment"},{"id":"2506.05967","title":"Preference Learning for AI Alignment: a Causal Perspective","created":"2025-06-06","cited_by_count":6,"area":"alignment"},{"id":"2503.03039","title":"LLM Misalignment via Adversarial RLHF Platforms","created":"2025-03-04","cited_by_count":5,"area":"alignment"},{"id":"2504.02193","title":"More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment","created":"2025-04-03","cited_by_count":5,"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":"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":"2605.11134","title":"Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training","created":"2026-05-11","cited_by_count":5,"area":"alignment"},{"id":"2503.15880","title":"InCo-DPO: Balancing Distribution Shift and Data Quality for Enhanced Preference Optimization","created":"2025-03-20","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":"2508.01930","title":"Word Overuse and Alignment in Large Language Models: The Influence of Learning from Human Feedback","created":"2025-08-03","cited_by_count":2,"area":"alignment"},{"id":"2602.06669","title":"compar:IA: The French Government's LLM arena to collect French-language human prompts and preference data","created":"2026-02-06","cited_by_count":2,"area":"alignment"},{"id":"2506.12382","title":"Exploring the Secondary Risks of Large Language Models","created":"2025-06-14","cited_by_count":1,"area":"alignment"},{"id":"2609.12651","title":"Distortion of AI Alignment Revisited: RLHF is a Decent Utilitarian Aligner","created":"2026-09-11","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":"2606.00334","title":"Isolating LLM Lexical Bias: A Curation-Free Triangulated Metric for Preference-Stage Learning","created":"2026-05-29","cited_by_count":0,"area":"alignment"},{"id":"2606.03165","title":"Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models","created":"2026-06-02","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"},{"id":"2609.00699","title":"Patterning in Practice: Debiasing Reward Models with Susceptibilities","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.32720","title":"BiasReducer: Adaptive Bias Mitigation for Reward Models","created":"2026-09-26","cited_by_count":0,"area":"alignment"},{"id":"2609.33989","title":"RewardExplainer: Learning Reward Model Explanations from Counterfactual Preference Feedback","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2609.35044","title":"BA-DPO: Bias-Adjusted Direct Preference Optimization for Language Model Alignment","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2610.19832","title":"Rent-Seeking Language Models: Reward Models Set the Prices, Frequent Audits Curb the Rent","created":"2026-10-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}