{"total":29,"rows":[{"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":"2409.17407","title":"Post-hoc Reward Calibration: A Case Study on Length Bias","created":"2024-09-25","cited_by_count":29,"area":"alignment"},{"id":"2409.06691","title":"Geometric-Averaged Preference Optimization for Soft Preference Labels","created":"2024-09-10","cited_by_count":18,"area":"alignment"},{"id":"2503.02832","title":"AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation","created":"2025-03-04","cited_by_count":17,"area":"alignment"},{"id":"2411.01493","title":"Sample-Efficient Alignment for LLMs","created":"2024-11-03","cited_by_count":16,"area":"alignment"},{"id":"2506.12109","title":"Personalized LLM Decoding via Contrasting Personal Preference","created":"2025-06-13","cited_by_count":12,"area":"alignment"},{"id":"2503.04647","title":"Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment","created":"2025-03-06","cited_by_count":9,"area":"alignment"},{"id":"2409.06411","title":"Length Desensitization in Direct Preference Optimization","created":"2024-09-10","cited_by_count":8,"area":"alignment"},{"id":"2506.07492","title":"Explicit Preference Optimization: No Need for an Implicit Reward Model","created":"2025-06-09","cited_by_count":6,"area":"alignment"},{"id":"2407.02119","title":"Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning","created":"2024-07-02","cited_by_count":5,"area":"alignment"},{"id":"2410.09362","title":"SeRA: Self-Reviewing and Alignment of Large Language Models using Implicit Reward Margins","created":"2024-10-12","cited_by_count":5,"area":"alignment"},{"id":"2504.11337","title":"REWARD CONSISTENCY: Improving Multi-Objective Alignment from a Data-Centric Perspective","created":"2025-04-15","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":"2510.02341","title":"DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning","created":"2025-09-27","cited_by_count":5,"area":"alignment"},{"id":"2509.23371","title":"Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization","created":"2025-09-27","cited_by_count":3,"area":"alignment"},{"id":"2601.20838","title":"Reward Models Inherit Value Biases from Pretraining","created":"2026-01-28","cited_by_count":3,"area":"alignment"},{"id":"2509.08541","title":"CM-Align: Consistency-based Multilingual Alignment for Large Language Models","created":"2025-09-10","cited_by_count":2,"area":"alignment"},{"id":"2411.02481","title":"Dr. SoW: Density Ratio of Strong-over-weak LLMs for Reducing the Cost of Human Annotation in Preference Tuning","created":"2024-11-04","cited_by_count":1,"area":"alignment"},{"id":"2502.18679","title":"Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data","created":"2025-02-25","cited_by_count":1,"area":"alignment"},{"id":"2504.14177","title":"Direct Advantage Regression: Aligning LLMs with Online AI Reward","created":"2025-04-19","cited_by_count":1,"area":"alignment"},{"id":"2605.15464","title":"GRLO: Towards Generalizable Reinforcement Learning in Open-Ended Environments from Zero","created":"2026-05-14","cited_by_count":1,"area":"alignment"},{"id":"2507.07855","title":"DPO Unchained: Your Training Algorithm is Secretly Disentangled in Human Choice Theory (and its Loss' Convexity is Dispensable)","created":"2025-07-10","cited_by_count":0,"area":"alignment"},{"id":"2511.12867","title":"Bootstrapping LLMs via Preference-Based Policy Optimization","created":"2025-11-17","cited_by_count":0,"area":"alignment"},{"id":"2601.06108","title":"From RLHF to Direct Alignment: A Theoretical Unification of Preference Learning for Large Language Models","created":"2026-01-03","cited_by_count":0,"area":"alignment"},{"id":"2602.08819","title":"Bayesian Preference Learning for Test-Time Steerable Reward Models","created":"2026-02-09","cited_by_count":0,"area":"alignment"},{"id":"2608.09568","title":"Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2608.27032","title":"Disentangling Optimization Scale from Preference Scale in DPO","created":"2026-08-27","cited_by_count":0,"area":"alignment"},{"id":"2609.05899","title":"AlignDiff: Exploiting Model-Intrinsic Information for Better Preference Data Selection","created":"2026-09-05","cited_by_count":0,"area":"alignment"},{"id":"2609.30226","title":"PoEM: Predicting RL Outcomes from Existing Policies","created":"2026-09-24","cited_by_count":0,"area":"alignment"}],"next_cursor":null}