{"total":21,"rows":[{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150,"area":"alignment"},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055,"area":"alignment"},{"id":"2402.00782","title":"Dense Reward for Free in Reinforcement Learning from Human Feedback","created":"2024-02-01","cited_by_count":78,"area":"alignment"},{"id":"1805.10627","title":"Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning","created":"2018-05-27","cited_by_count":57,"area":"alignment"},{"id":"2311.06025","title":"ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences","created":"2023-11-10","cited_by_count":43,"area":"alignment"},{"id":"2202.09662","title":"Reward Modeling for Mitigating Toxicity in Transformer-based Language Models","created":"2022-02-19","cited_by_count":18,"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":"2407.16637","title":"Course-Correction: Safety Alignment Using Synthetic Preferences","created":"2024-07-23","cited_by_count":13,"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":"2109.11136","title":"Non-Parametric Online Learning from Human Feedback for Neural Machine Translation","created":"2021-09-23","cited_by_count":8,"area":"alignment"},{"id":"2503.04793","title":"Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference","created":"2025-03-01","cited_by_count":5,"area":"alignment"},{"id":"2602.16832","title":"IndicJR: A Judge-Free Benchmark of Jailbreak Robustness in South Asian Languages","created":"2026-02-18","cited_by_count":5,"area":"alignment"},{"id":"2403.04187","title":"Preference optimization of protein language models as a multi-objective binder design paradigm","created":"2024-03-07","cited_by_count":4,"area":"alignment"},{"id":"2407.03232","title":"Single Character Perturbations Break LLM Alignment","created":"2024-07-03","cited_by_count":4,"area":"alignment"},{"id":"2010.11553","title":"Incorporating Stylistic Lexical Preferences in Generative Language Models","created":"2020-10-22","cited_by_count":2,"area":"alignment"},{"id":"2507.08898","title":"SEALGuard: Safeguarding the Multilingual Conversations in Southeast Asian Languages for LLM Software Systems","created":"2025-07-11","cited_by_count":2,"area":"alignment"},{"id":"2506.04464","title":"Leveraging Reward Models for Guiding Code Review Comment Generation","created":"2025-06-04","cited_by_count":1,"area":"alignment"},{"id":"2604.27401","title":"Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs","created":"2026-04-30","cited_by_count":1,"area":"alignment"},{"id":"2410.06118","title":"Optimizing the Training Schedule of Multilingual NMT using Reinforcement Learning","created":"2024-10-08","cited_by_count":0,"area":"alignment"},{"id":"2505.06284","title":"DMRL: Data- and Model-aware Reward Learning for Data Extraction","created":"2025-05-07","cited_by_count":0,"area":"alignment"},{"id":"2607.01239","title":"Breaking Safety at the Token Boundary: How BPE Tokenization Creates Exploitable Gaps in LLM Alignment","created":"2026-05-01","cited_by_count":0,"area":"alignment"}],"next_cursor":null}