{"total":33,"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":"2209.13085","title":"Defining and Characterizing Reward Hacking","created":"2022-09-27","cited_by_count":203,"area":"alignment"},{"id":"2403.19159","title":"Disentangling Length from Quality in Direct Preference Optimization","created":"2024-03-28","cited_by_count":196,"area":"alignment"},{"id":"2406.02900","title":"Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms","created":"2024-06-05","cited_by_count":143,"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":"2409.15268","title":"Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking","created":"2024-09-23","cited_by_count":35,"area":"alignment"},{"id":"2309.16155","title":"The Trickle-down Impact of Reward (In-)consistency on RLHF","created":"2023-09-28","cited_by_count":29,"area":"alignment"},{"id":"2505.12763","title":"Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization","created":"2025-05-19","cited_by_count":11,"area":"alignment"},{"id":"2509.05381","title":"Murphys Laws of AI Alignment: Why the Gap Always Wins","created":"2025-09-04","cited_by_count":5,"area":"alignment"},{"id":"2409.19024","title":"Elephant in the Room: Unveiling the Impact of Reward Model Quality in Alignment","created":"2024-09-26","cited_by_count":4,"area":"alignment"},{"id":"2502.04675","title":"Scalable Oversight for Superhuman AI via Recursive Self-Critiquing","created":"2025-02-07","cited_by_count":4,"area":"alignment"},{"id":"2609.04665","title":"Harness-agnostic detection and immunization of reward hacking in self-evolving language models","created":"2026-09-04","cited_by_count":3,"area":"alignment"},{"id":"2503.12301","title":"One Goal, Many Challenges: Robust Preference Optimization Amid Content-Aware and Multi-Source Noise","created":"2025-03-16","cited_by_count":2,"area":"alignment"},{"id":"2510.03231","title":"Reward Models are Metrics in a Trench Coat","created":"2025-10-03","cited_by_count":2,"area":"alignment"},{"id":"2603.04861","title":"Causally Robust Reward Learning from Reason-Augmented Preference Feedback","created":"2026-03-05","cited_by_count":2,"area":"alignment"},{"id":"2512.03048","title":"The Specification Trap: Why Static Value Alignment Alone Is Insufficient for Robust Alignment","created":"2025-11-19","cited_by_count":1,"area":"alignment"},{"id":"2604.17769","title":"Reverse Constitutional AI: A Framework for Controllable Toxic Data Generation via Probability-Clamped RLAIF","created":"2026-04-20","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":"1809.01036","title":"A Roadmap for Robust End-to-End Alignment","created":"2018-09-04","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":"2604.05274","title":"Simulating the Evolution of Alignment and Values in Machine Intelligence","created":"2026-04-07","cited_by_count":0,"area":"alignment"},{"id":"2606.08893","title":"Cheap Reward Hacking Detection","created":"2026-06-08","cited_by_count":0,"area":"alignment"},{"id":"2606.27291","title":"Designing Reward Signals for Portable Query Generation: A Case Study in Industrial Semantic Job Search","created":"2026-06-25","cited_by_count":0,"area":"alignment"},{"id":"2606.28710","title":"The Two Genie Game: Adoption and Welfare in Audit-Grounded AI Governance","created":"2026-06-27","cited_by_count":0,"area":"alignment"},{"id":"2607.28881","title":"Fragility of Value under Imperfect Alignment","created":"2026-07-30","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":"2610.02568","title":"Mitigating Social Sycophancy via Pluralistic Preference Optimization","created":"2026-10-01","cited_by_count":0,"area":"alignment"},{"id":"2610.11281","title":"How to post-train on a surrogate: Envelope sampling mitigates reward hacking","created":"2026-10-08","cited_by_count":0,"area":"alignment"},{"id":"2610.15008","title":"Can You Trust Your Preference Models? Stackelberg Games for Alignment","created":"2026-10-10","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":"2610.19832","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}