{"total":25,"rows":[{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"area":"alignment"},{"id":"2507.00769","title":"LitBench: A Benchmark and Dataset for Reliable Evaluation of Creative Writing","created":"2025-07-01","cited_by_count":42,"area":"alignment"},{"id":"2509.03403","title":"Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training","created":"2025-09-03","cited_by_count":29,"area":"alignment"},{"id":"2511.21654","title":"EvilGenie: A Reward Hacking Benchmark","created":"2025-11-26","cited_by_count":28,"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":"2409.02795","title":"Towards a Unified View of Preference Learning for Large Language Models: A Survey","created":"2024-09-04","cited_by_count":17,"area":"alignment"},{"id":"2506.20495","title":"ReCode: Updating Code API Knowledge with Reinforcement Learning","created":"2025-06-25","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":"2603.01246","title":"Defensive Refusal Bias: How Safety Alignment Fails Cyber Defenders","created":"2026-03-01","cited_by_count":10,"area":"alignment"},{"id":"2605.20744","title":"Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale","created":"2026-05-20","cited_by_count":10,"area":"alignment"},{"id":"2601.03525","title":"Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Learning in Code Generation","created":"2026-01-07","cited_by_count":5,"area":"alignment"},{"id":"2508.13993","title":"Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization","created":"2025-08-19","cited_by_count":3,"area":"alignment"},{"id":"2510.18081","title":"Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth","created":"2025-10-20","cited_by_count":3,"area":"alignment"},{"id":"2609.19101","title":"Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations","created":"2026-09-16","cited_by_count":2,"area":"alignment"},{"id":"2406.16377","title":"On the Transformations across Reward Model, Parameter Update, and In-Context Prompt","created":"2024-06-24","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":"2607.14240","title":"Align AI to Dynamic Human-AI Workflows","created":"2026-07-15","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":"2609.36308","title":"CheatBench: Measuring Reward Gaming in AI Agents","created":"2026-09-28","cited_by_count":1,"area":"alignment"},{"id":"2605.19665","title":"CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging","created":"2026-05-19","cited_by_count":0,"area":"alignment"},{"id":"2606.28998","title":"Reward-Free Code Alignment from Pretrained or Fine-Tuned LLM: Unpacking the Trade-offs for Code Generation","created":"2026-06-27","cited_by_count":0,"area":"alignment"},{"id":"2608.08491","title":"TrustRoboReward: Preference-Ordered Isotonic Score Editing for Multi-Paradigm Robot Reward Models","created":"2026-08-09","cited_by_count":0,"area":"alignment"},{"id":"2609.01597","title":"The Rise of Verbal Reinforcement Learning","created":"2026-09-01","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}