{"total":28,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971,"area":"alignment"},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2302.07459","title":"The Capacity for Moral Self-Correction in Large Language Models","created":"2023-02-15","cited_by_count":173,"area":"alignment"},{"id":"2304.11082","title":"Fundamental Limitations of Alignment in Large Language Models","created":"2023-04-19","cited_by_count":155,"area":"alignment"},{"id":"2303.05453","title":"Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback","created":"2023-03-09","cited_by_count":87,"area":"alignment"},{"id":"2405.17977","title":"Aligning to Thousands of Preferences via System Message Generalization","created":"2024-05-28","cited_by_count":84,"area":"alignment"},{"id":"2405.09719","title":"Spectral Editing of Activations for Large Language Model Alignment","created":"2024-05-15","cited_by_count":56,"area":"alignment"},{"id":"2308.12014","title":"From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models","created":"2023-08-23","cited_by_count":45,"area":"alignment"},{"id":"2311.04072","title":"Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment","created":"2023-11-07","cited_by_count":35,"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":"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":"2511.03369","title":"Silenced Biases: The Dark Side LLMs Learned to Refuse","created":"2025-11-05","cited_by_count":10,"area":"alignment"},{"id":"2404.18870","title":"More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness","created":"2024-04-29","cited_by_count":9,"area":"alignment"},{"id":"2505.23349","title":"Towards Reward Fairness in RLHF: From a Resource Allocation Perspective","created":"2025-05-29","cited_by_count":9,"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":"2508.05553","title":"Do Political Opinions Transfer Between Western Languages? An Analysis of Unaligned and Aligned Multilingual LLMs","created":"2025-08-07","cited_by_count":6,"area":"alignment"},{"id":"2411.03700","title":"The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models","created":"2024-11-06","cited_by_count":5,"area":"alignment"},{"id":"2501.17117","title":"Histoires Morales: A French Dataset for Assessing Moral Alignment","created":"2025-01-28","cited_by_count":4,"area":"alignment"},{"id":"2509.13869","title":"Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs","created":"2025-09-17","cited_by_count":3,"area":"alignment"},{"id":"2503.07806","title":"Towards Large Language Models that Benefit for All: Benchmarking Group Fairness in Reward Models","created":"2025-03-10","cited_by_count":2,"area":"alignment"},{"id":"2605.05003","title":"Misaligned by Reward: Socially Undesirable Preferences in LLMs","created":"2026-05-06","cited_by_count":1,"area":"alignment"},{"id":"2606.04807","title":"BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimization","created":"2026-06-03","cited_by_count":1,"area":"alignment"},{"id":"2505.10775","title":"A Systematic Analysis of Base Model Choice for Reward Modeling","created":"2025-05-16","cited_by_count":0,"area":"alignment"},{"id":"2512.10601","title":"Multi-Objective Reward and Preference Optimization: Theory and Algorithms","created":"2025-12-11","cited_by_count":0,"area":"alignment"},{"id":"2605.26738","title":"KARMA: Karma-Aligned Reward Model Adaptation","created":"2026-05-26","cited_by_count":0,"area":"alignment"},{"id":"2608.18131","title":"Safety Alignment Illusion: The Cross-Lingual Safety Gap in LLMs","created":"2026-07-26","cited_by_count":0,"area":"alignment"},{"id":"2608.29492","title":"CoCoA: Context-Conditional Cultural Alignment for Large Language Models","created":"2026-08-30","cited_by_count":0,"area":"alignment"},{"id":"2609.14860","title":"One Example Is Enough to Pass Fairness Benchmarks: Rethinking Fairness Evaluation for Aligned LLMs","created":"2026-09-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}