{"total":29,"rows":[{"id":"2404.10719","title":"Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study","created":"2024-04-16","cited_by_count":262,"area":"alignment"},{"id":"2402.13228","title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","created":"2024-02-20","cited_by_count":241,"area":"alignment"},{"id":"2409.12822","title":"Language Models Learn to Mislead Humans via RLHF","created":"2024-09-19","cited_by_count":124,"area":"alignment"},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"area":"alignment"},{"id":"2403.09032","title":"CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences","created":"2024-03-14","cited_by_count":57,"area":"alignment"},{"id":"2409.20370","title":"The Perfect Blend: Redefining RLHF with Mixture of Judges","created":"2024-09-30","cited_by_count":43,"area":"alignment"},{"id":"2306.04930","title":"When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming","created":"2023-06-08","cited_by_count":25,"area":"alignment"},{"id":"2510.06186","title":"RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback","created":"2025-10-07","cited_by_count":25,"area":"alignment"},{"id":"2505.23387","title":"Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization","created":"2025-05-29","cited_by_count":18,"area":"alignment"},{"id":"2408.11296","title":"RePair: Automated Program Repair with Process-based Feedback","created":"2024-08-21","cited_by_count":16,"area":"alignment"},{"id":"2410.02743","title":"MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions","created":"2024-10-03","cited_by_count":15,"area":"alignment"},{"id":"2501.02790","title":"Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model","created":"2025-01-06","cited_by_count":12,"area":"alignment"},{"id":"2506.00419","title":"Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences","created":"2025-05-31","cited_by_count":10,"area":"alignment"},{"id":"2311.07723","title":"Generalization Analogies: A Testbed for Generalizing AI Oversight to Hard-To-Measure Domains","created":"2023-11-13","cited_by_count":8,"area":"alignment"},{"id":"2605.01123","title":"PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs","created":"2026-05-01","cited_by_count":6,"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":"2508.19532","title":"Alignment with Fill-In-the-Middle for Enhancing Code Generation","created":"2025-08-27","cited_by_count":4,"area":"alignment"},{"id":"2504.15210","title":"Integrating Symbolic Execution into the Fine-Tuning of Code-Generating LLMs","created":"2025-04-21","cited_by_count":2,"area":"alignment"},{"id":"2505.12723","title":"On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language Understanding","created":"2025-05-19","cited_by_count":2,"area":"alignment"},{"id":"2602.01685","title":"Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment","created":"2026-02-02","cited_by_count":2,"area":"alignment"},{"id":"2605.08037","title":"Beyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph","created":"2026-05-08","cited_by_count":2,"area":"alignment"},{"id":"2507.20109","title":"Learning to Align Human Code Preferences","created":"2025-07-27","cited_by_count":1,"area":"alignment"},{"id":"2603.04355","title":"Efficient Refusal Ablation in LLM through Optimal Transport","created":"2026-03-04","cited_by_count":1,"area":"alignment"},{"id":"2603.29292","title":"Self-Improving Code Generation via Semantic Entropy and Behavioral Consensus","created":"2026-03-31","cited_by_count":1,"area":"alignment"},{"id":"2605.09134","title":"BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models","created":"2026-05-09","cited_by_count":1,"area":"alignment"},{"id":"2608.27906","title":"Design the Feedback, Not Just the Reward: Environments for Open-Ended Reinforcement Learning","created":"2026-08-28","cited_by_count":1,"area":"alignment"},{"id":"2510.23083","title":"Smaller Models, Smarter Rewards: A Two-Sided Approach to Process and Outcome Rewards","created":"2025-10-27","cited_by_count":0,"area":"alignment"},{"id":"2609.06649","title":"Inducing Emergent Misalignment from Reward Hacks with Iterative DPO","created":"2026-09-06","cited_by_count":0,"area":"alignment"},{"id":"2609.29421","title":"Rufus-Air: An Open LLM Post-Training Recipe","created":"2026-09-24","cited_by_count":0,"area":"alignment"}],"next_cursor":null}