{"total":48,"rows":[{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095,"area":"alignment"},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500,"area":"alignment"},{"id":"2406.12845","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","created":"2024-06-18","cited_by_count":376,"area":"alignment"},{"id":"2310.03716","title":"A Long Way to Go: Investigating Length Correlations in RLHF","created":"2023-10-05","cited_by_count":291,"area":"alignment"},{"id":"2310.05199","title":"Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback","created":"2023-10-08","cited_by_count":78,"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":"2403.03185","title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking","created":"2024-03-05","cited_by_count":50,"area":"alignment"},{"id":"2404.05530","title":"Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data","created":"2024-04-08","cited_by_count":35,"area":"alignment"},{"id":"2310.11971","title":"Improving Generalization of Alignment with Human Preferences through Group Invariant Learning","created":"2023-10-18","cited_by_count":25,"area":"alignment"},{"id":"2301.03652","title":"On The Fragility of Learned Reward Functions","created":"2023-01-09","cited_by_count":21,"area":"alignment"},{"id":"2505.02666","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","created":"2025-05-05","cited_by_count":15,"area":"alignment"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2503.00069","title":"Societal Alignment Frameworks Can Improve LLM Alignment","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2402.02479","title":"BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback","created":"2024-02-04","cited_by_count":7,"area":"alignment"},{"id":"2604.01476","title":"From Rebound to Remedy: Understanding and Mitigating Reward Hacking via Representation Engineering","created":"2026-04-01","cited_by_count":7,"area":"alignment"},{"id":"2507.18742","title":"Specification Self-Correction: Mitigating In-Context Reward Hacking Through Test-Time Refinement","created":"2025-07-24","cited_by_count":6,"area":"alignment"},{"id":"2503.22137","title":"Sharpe Ratio-Guided Active Learning for Preference Optimization in RLHF","created":"2025-03-28","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":"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":"2308.06385","title":"ZYN: Zero-Shot Reward Models with Yes-No Questions for RLAIF","created":"2023-08-11","cited_by_count":4,"area":"alignment"},{"id":"2510.08048","title":"TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance","created":"2025-10-09","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":"2608.17776","title":"Debate Training Reduces Reward Hacking in RLAIF","created":"2026-08-18","cited_by_count":4,"area":"alignment"},{"id":"2502.00136","title":"A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment","created":"2025-01-31","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":"2607.18966","title":"Measuring Reward-Seeking via Contrastive Belief Updates","created":"2026-07-21","cited_by_count":3,"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":"2609.13150","title":"The Limits of Reference-Free Speech Quality Metrics as Evaluators and Rewards on Modern Text-to-Speech","created":"2026-07-02","cited_by_count":2,"area":"alignment"},{"id":"2407.16025","title":"Exploring and Addressing Reward Confusion in Offline Preference Learning","created":"2024-07-22","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":"2510.21090","title":"Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only","created":"2025-10-24","cited_by_count":1,"area":"alignment"},{"id":"2511.16202","title":"Multi-Agent Collaborative Reward Design for Enhancing Reasoning in Reinforcement Learning","created":"2025-11-20","cited_by_count":1,"area":"alignment"},{"id":"2604.26360","title":"Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking","created":"2026-04-29","cited_by_count":1,"area":"alignment"},{"id":"2606.04145","title":"EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms","created":"2026-06-02","cited_by_count":1,"area":"alignment"},{"id":"2606.06133","title":"TLA-Prover: Verifiable TLA+ Specification Synthesis via Preference-Optimized Low-Rank Adaptation","created":"2026-06-04","cited_by_count":1,"area":"alignment"},{"id":"2606.09073","title":"A Unifying Lens on Reward Uncertainty in RLHF","created":"2026-06-08","cited_by_count":1,"area":"alignment"},{"id":"2312.14436","title":"REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback","created":"2023-12-22","cited_by_count":0,"area":"alignment"},{"id":"2602.04651","title":"SAFE: Stable Alignment Finetuning with Entropy-Aware Predictive Control for Reinforcement Learning from Human Feedback (RLHF)","created":"2026-02-04","cited_by_count":0,"area":"alignment"},{"id":"2603.29993","title":"Extending MONA in Camera Dropbox: Reproduction, Learned Approval, and Design Implications for Reward-Hacking Mitigation","created":"2026-03-31","cited_by_count":0,"area":"alignment"},{"id":"2604.04237","title":"Pedagogical Safety in Educational Reinforcement Learning: Formalizing and Detecting Reward Hacking in AI Tutoring Systems","created":"2026-04-05","cited_by_count":0,"area":"alignment"},{"id":"2604.24155","title":"The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers","created":"2026-04-27","cited_by_count":0,"area":"alignment"},{"id":"2606.24622","title":"Themis: An explainable AI-enabled framework for Reinforcement Learning with Human Feedback","created":"2026-06-23","cited_by_count":0,"area":"alignment"},{"id":"2609.38526","title":"Revisiting scaling laws for reward optimization","created":"2026-09-29","cited_by_count":0,"area":"alignment"},{"id":"2610.03458","title":"A Near-Zero Monitor Readout Is Not Evidence of Behavioral Control","created":"2026-10-02","cited_by_count":0,"area":"alignment"},{"id":"2610.04793","title":"Pressure, Context, and Machine Self-Control: A Criminological Test of Reward Hacking in Generative AI Models","created":"2026-10-03","cited_by_count":0,"area":"alignment"},{"id":"2610.17062","title":"Gradient Routing Localizes and Removes Unintended Behaviors in RL","created":"2026-10-12","cited_by_count":0,"area":"alignment"},{"id":"2610.19525","title":"Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following","created":"2026-10-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}