{"total":35,"rows":[{"id":"2404.13076","title":"LLM Evaluators Recognize and Favor Their Own Generations","created":"2024-04-15","cited_by_count":686,"area":"alignment"},{"id":"2312.09244","title":"Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking","created":"2023-12-14","cited_by_count":200,"area":"alignment"},{"id":"2403.08635","title":"Human Alignment of Large Language Models through Online Preference Optimisation","created":"2024-03-13","cited_by_count":91,"area":"alignment"},{"id":"2407.14622","title":"BOND: Aligning LLMs with Best-of-N Distillation","created":"2024-07-19","cited_by_count":76,"area":"alignment"},{"id":"2402.02992","title":"Decoding-time Realignment of Language Models","created":"2024-02-05","cited_by_count":67,"area":"alignment"},{"id":"2402.06147","title":"DeAL: Decoding-time Alignment for Large Language Models","created":"2024-02-05","cited_by_count":55,"area":"alignment"},{"id":"2408.11491","title":"SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering","created":"2024-08-21","cited_by_count":50,"area":"alignment"},{"id":"2212.09968","title":"On Improving Summarization Factual Consistency from Natural Language Feedback","created":"2022-12-20","cited_by_count":38,"area":"alignment"},{"id":"2306.00398","title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning","created":"2023-06-01","cited_by_count":31,"area":"alignment"},{"id":"2404.12318","title":"Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment","created":"2024-04-18","cited_by_count":26,"area":"alignment"},{"id":"2506.17871","title":"LLM Probability Concentration: How Alignment Shrinks the Generative Horizon","created":"2025-06-22","cited_by_count":26,"area":"alignment"},{"id":"2412.10432","title":"Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection","created":"2024-12-11","cited_by_count":23,"area":"alignment"},{"id":"2505.13388","title":"R3: Robust Rubric-Agnostic Reward Models","created":"2025-05-19","cited_by_count":23,"area":"alignment"},{"id":"2410.18640","title":"Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model","created":"2024-10-24","cited_by_count":22,"area":"alignment"},{"id":"2406.01660","title":"Self-Improving Robust Preference Optimization","created":"2024-06-03","cited_by_count":19,"area":"alignment"},{"id":"2405.17382","title":"ReMoDetect: Reward Models Recognize Aligned LLM's Generations","created":"2024-05-27","cited_by_count":11,"area":"alignment"},{"id":"2409.00162","title":"Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback","created":"2024-08-30","cited_by_count":9,"area":"alignment"},{"id":"2403.06326","title":"From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification","created":"2024-03-10","cited_by_count":8,"area":"alignment"},{"id":"2409.18618","title":"Model-based Preference Optimization in Abstractive Summarization without Human Feedback","created":"2024-09-27","cited_by_count":7,"area":"alignment"},{"id":"2310.19347","title":"Improving Factual Consistency of News Summarization by Contrastive Preference Optimization","created":"2023-10-30","cited_by_count":6,"area":"alignment"},{"id":"2501.13264","title":"OpenGenAlign: A Preference Dataset and Benchmark for Trustworthy Reward Modeling in Open-Ended, Long-Context Generation","created":"2025-01-22","cited_by_count":5,"area":"alignment"},{"id":"2410.00409","title":"AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference","created":"2024-10-01","cited_by_count":4,"area":"alignment"},{"id":"2412.10689","title":"Learning to Verify Summary Facts with Fine-Grained LLM Feedback","created":"2024-12-14","cited_by_count":4,"area":"alignment"},{"id":"2502.19255","title":"Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective","created":"2025-02-26","cited_by_count":4,"area":"alignment"},{"id":"2509.03647","title":"Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators","created":"2025-09-03","cited_by_count":3,"area":"alignment"},{"id":"2508.09016","title":"A Survey on Training-free Alignment of Large Language Models","created":"2025-08-12","cited_by_count":2,"area":"alignment"},{"id":"2602.06869","title":"Uncovering Cross-Objective Interference in Multi-Objective Alignment","created":"2026-02-06","cited_by_count":2,"area":"alignment"},{"id":"2408.16753","title":"Reinforcement Learning without Human Feedback for Last Mile Fine-Tuning of Large Language Models","created":"2024-08-29","cited_by_count":1,"area":"alignment"},{"id":"2511.06942","title":"HLPD: Aligning LLMs to Human Language Preference for Machine-Revised Text Detection","created":"2025-11-10","cited_by_count":1,"area":"alignment"},{"id":"2604.16923","title":"Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy","created":"2026-04-18","cited_by_count":1,"area":"alignment"},{"id":"2605.30808","title":"Differentially Private Preference Data Synthesis for Large Language Model Alignment","created":"2026-05-29","cited_by_count":1,"area":"alignment"},{"id":"2406.01070","title":"Guiding ChatGPT to Generate Salient Domain Summaries","created":"2024-06-03","cited_by_count":0,"area":"alignment"},{"id":"2605.26840","title":"Optimising Factual Consistency in Summarisation via Preference Learning from Multiple Imperfect Metrics","created":"2026-05-26","cited_by_count":0,"area":"alignment"},{"id":"2607.27366","title":"BridgeAlign: Bridging Preference Alignment for Humanities and Social Sciences","created":"2026-07-29","cited_by_count":0,"area":"alignment"},{"id":"2610.04998","title":"EmoRSS: Mitigating Emotion-Induced Over-Refusal in Large Language Models","created":"2026-10-04","cited_by_count":0,"area":"alignment"}],"next_cursor":null}