{"total":36,"rows":[{"id":"2409.12822","title":"Language Models Learn to Mislead Humans via RLHF","created":"2024-09-19","cited_by_count":124,"area":"alignment"},{"id":"2502.18770","title":"Reward Shaping to Mitigate Reward Hacking in RLHF","created":"2025-02-26","cited_by_count":88,"area":"alignment"},{"id":"2402.05369","title":"Noise Contrastive Alignment of Language Models with Explicit Rewards","created":"2024-02-08","cited_by_count":85,"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":"2511.07919","title":"Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison","created":"2025-11-11","cited_by_count":44,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2408.15313","title":"Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models","created":"2024-08-27","cited_by_count":27,"area":"alignment"},{"id":"2411.12882","title":"ProSec: Fortifying Code LLMs with Proactive Security Alignment","created":"2024-11-19","cited_by_count":25,"area":"alignment"},{"id":"2409.06957","title":"Policy Filtration for RLHF to Mitigate Noise in Reward Models","created":"2024-09-11","cited_by_count":22,"area":"alignment"},{"id":"2412.05210","title":"Evaluating and Aligning CodeLLMs on Human Preference","created":"2024-12-06","cited_by_count":22,"area":"alignment"},{"id":"2502.11555","title":"Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models","created":"2025-02-17","cited_by_count":22,"area":"alignment"},{"id":"2405.16661","title":"RLSF: Fine-tuning LLMs via Symbolic Feedback","created":"2024-05-26","cited_by_count":14,"area":"alignment"},{"id":"2504.15804","title":"Insights from Verification: Training a Verilog Generation LLM with Reinforcement Learning with Testbench Feedback","created":"2025-04-22","cited_by_count":14,"area":"alignment"},{"id":"2406.11715","title":"Measuring memorization in RLHF for code completion","created":"2024-06-17","cited_by_count":13,"area":"alignment"},{"id":"2412.01253","title":"Yi-Lightning Technical Report","created":"2024-12-02","cited_by_count":12,"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":"2512.11391","title":"Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization","created":"2025-12-12","cited_by_count":11,"area":"alignment"},{"id":"2405.11647","title":"Hummer: Towards Limited Competitive Preference Dataset","created":"2024-05-19","cited_by_count":10,"area":"alignment"},{"id":"2503.02783","title":"Teaching Your Models to Understand Code via Focal Preference Alignment","created":"2025-03-04","cited_by_count":10,"area":"alignment"},{"id":"2410.18585","title":"Aligning CodeLLMs with Direct Preference Optimization","created":"2024-10-24","cited_by_count":9,"area":"alignment"},{"id":"2406.06887","title":"$\\textbf{PLUM}$: Improving Code LMs with Execution-Guided On-Policy Preference Learning Driven By Synthetic Test Cases","created":"2024-06-11","cited_by_count":8,"area":"alignment"},{"id":"2410.21349","title":"FALCON: Feedback-driven Adaptive Long/short-term memory reinforced Coding Optimization system","created":"2024-10-28","cited_by_count":8,"area":"alignment"},{"id":"2502.16645","title":"CODESYNC: Synchronizing Large Language Models with Dynamic Code Evolution at Scale","created":"2025-02-23","cited_by_count":8,"area":"alignment"},{"id":"2409.04183","title":"GALLa: Graph Aligned Large Language Models for Improved Source Code Understanding","created":"2024-09-06","cited_by_count":7,"area":"alignment"},{"id":"2505.12380","title":"Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward","created":"2025-05-18","cited_by_count":7,"area":"alignment"},{"id":"2602.07422","title":"Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model","created":"2026-02-07","cited_by_count":6,"area":"alignment"},{"id":"2602.17684","title":"CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models","created":"2026-02-04","cited_by_count":5,"area":"alignment"},{"id":"2404.18410","title":"Mixture-of-Instructions: Aligning Large Language Models via Mixture Prompting","created":"2024-04-29","cited_by_count":4,"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":"2506.02460","title":"MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework","created":"2025-06-03","cited_by_count":3,"area":"alignment"},{"id":"2505.18799","title":"ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models","created":"2025-05-24","cited_by_count":2,"area":"alignment"},{"id":"2605.10141","title":"FormalRewardBench: A Benchmark for Formal Theorem Proving Reward Models","created":"2026-05-11","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":"2604.18327","title":"PARM: Pipeline-Adapted Reward Model","created":"2026-04-20","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":"2609.39902","title":"CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion","created":"2026-09-30","cited_by_count":0,"area":"alignment"}],"next_cursor":null}