{"total":38,"rows":[{"id":"2310.02949","title":"Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models","created":"2023-10-04","cited_by_count":297,"area":"alignment"},{"id":"2406.15513","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference","created":"2024-06-20","cited_by_count":261,"area":"alignment"},{"id":"2402.02416","title":"Aligner: Efficient Alignment by Learning to Correct","created":"2024-02-04","cited_by_count":98,"area":"alignment"},{"id":"2402.09345","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","created":"2024-02-14","cited_by_count":79,"area":"alignment"},{"id":"2312.07000","title":"Alignment for Honesty","created":"2023-12-12","cited_by_count":74,"area":"alignment"},{"id":"2311.18743","title":"AlignBench: Benchmarking Chinese Alignment of Large Language Models","created":"2023-11-30","cited_by_count":68,"area":"alignment"},{"id":"2310.06762","title":"TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models","created":"2023-10-10","cited_by_count":66,"area":"alignment"},{"id":"2401.00243","title":"Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles","created":"2023-12-30","cited_by_count":56,"area":"alignment"},{"id":"2311.06899","title":"Flames: Benchmarking Value Alignment of LLMs in Chinese","created":"2023-11-12","cited_by_count":37,"area":"alignment"},{"id":"2409.15360","title":"Reward-Robust RLHF in LLMs","created":"2024-09-18","cited_by_count":32,"area":"alignment"},{"id":"2406.07327","title":"3D-Properties: Identifying Challenges in DPO and Charting a Path Forward","created":"2024-06-11","cited_by_count":24,"area":"alignment"},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2406.13925","title":"GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models","created":"2024-06-20","cited_by_count":18,"area":"alignment"},{"id":"2402.16567","title":"Aligning Large Language Models to a Domain-specific Graph Database for NL2GQL","created":"2024-02-26","cited_by_count":14,"area":"alignment"},{"id":"2409.04340","title":"AGR: Age Group fairness Reward for Bias Mitigation in LLMs","created":"2024-09-06","cited_by_count":12,"area":"alignment"},{"id":"2502.19731","title":"Preference Learning Unlocks LLMs' Psycho-Counseling Skills","created":"2025-02-27","cited_by_count":10,"area":"alignment"},{"id":"2401.05695","title":"Integrating Physician Diagnostic Logic into Large Language Models: Preference Learning from Process Feedback","created":"2024-01-11","cited_by_count":9,"area":"alignment"},{"id":"2407.06542","title":"LIONs: An Empirically Optimized Approach to Align Language Models","created":"2024-07-09","cited_by_count":7,"area":"alignment"},{"id":"2410.14940","title":"Baichuan Alignment Technical Report","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2311.05374","title":"TencentLLMEval: A Hierarchical Evaluation of Real-World Capabilities for Human-Aligned LLMs","created":"2023-11-09","cited_by_count":5,"area":"alignment"},{"id":"2405.16964","title":"Exploring the LLM Journey from Cognition to Expression with Linear Representations","created":"2024-05-27","cited_by_count":5,"area":"alignment"},{"id":"2406.16486","title":"Towards Comprehensive Preference Data Collection for Reward Modeling","created":"2024-06-24","cited_by_count":5,"area":"alignment"},{"id":"2510.13694","title":"Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking","created":"2025-10-15","cited_by_count":5,"area":"alignment"},{"id":"2510.17833","title":"Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage","created":"2025-10-03","cited_by_count":5,"area":"alignment"},{"id":"2411.09341","title":"Approximated Variational Bayesian Inverse Reinforcement Learning for Large Language Model Alignment","created":"2024-11-14","cited_by_count":4,"area":"alignment"},{"id":"2508.06036","title":"More Is Better: A MoE-Based Emotion Recognition Framework with Human Preference Alignment","created":"2025-08-08","cited_by_count":4,"area":"alignment"},{"id":"2408.12579","title":"RuleAlign: Making Large Language Models Better Physicians with Diagnostic Rule Alignment","created":"2024-08-22","cited_by_count":3,"area":"alignment"},{"id":"2501.02869","title":"IIMedGPT: Promoting Large Language Model Capabilities of Medical Tasks by Efficient Human Preference Alignment","created":"2025-01-06","cited_by_count":3,"area":"alignment"},{"id":"2506.00835","title":"SynPO: Synergizing Descriptiveness and Preference Optimization for Video Detailed Captioning","created":"2025-06-01","cited_by_count":3,"area":"alignment"},{"id":"2509.19360","title":"Semantic Representation Attack against Aligned Large Language Models","created":"2025-09-18","cited_by_count":3,"area":"alignment"},{"id":"2405.19763","title":"Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding","created":"2024-05-30","cited_by_count":2,"area":"alignment"},{"id":"2504.05050","title":"Revealing the Intrinsic Ethical Vulnerability of Aligned Large Language Models","created":"2025-04-07","cited_by_count":2,"area":"alignment"},{"id":"2410.04112","title":"Exploring LLM-based Data Annotation Strategies for Medical Dialogue Preference Alignment","created":"2024-10-05","cited_by_count":1,"area":"alignment"},{"id":"2411.00897","title":"Enhancing the Traditional Chinese Medicine Capabilities of Large Language Model through Reinforcement Learning from AI Feedback","created":"2024-11-01","cited_by_count":1,"area":"alignment"},{"id":"2607.02291","title":"Optimizing Visual Generative Models via Distribution-wise Rewards","created":"2026-07-02","cited_by_count":1,"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":"2506.09329","title":"Towards Efficient and Effective Alignment of Large Language Models","created":"2025-06-11","cited_by_count":0,"area":"alignment"},{"id":"2608.09605","title":"TSPORec: Token Selection via Preference Optimization for LLM-Based Sequential Recommendation","created":"2026-08-10","cited_by_count":0,"area":"alignment"}],"next_cursor":null}