{"total":23,"rows":[{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2305.14291","title":"Evaluation of African American Language Bias in Natural Language Generation","created":"2023-05-23","cited_by_count":36,"area":null},{"id":"2210.04492","title":"Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization","created":"2022-10-10","cited_by_count":33,"area":null},{"id":"2408.03907","title":"Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models","created":"2024-08-07","cited_by_count":33,"area":null},{"id":"2212.10678","title":"Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2406.08723","title":"ECBD: Evidence-Centered Benchmark Design for NLP","created":"2024-06-13","cited_by_count":28,"area":null},{"id":"2311.16087","title":"DUnE: Dataset for Unified Editing","created":"2023-11-27","cited_by_count":19,"area":null},{"id":"2312.01509","title":"Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societies","created":"2023-12-03","cited_by_count":11,"area":null},{"id":"2305.12757","title":"This Prompt is Measuring <MASK>: Evaluating Bias Evaluation in Language Models","created":"2023-05-22","cited_by_count":9,"area":null},{"id":"2302.12640","title":"In-Depth Look at Word Filling Societal Bias Measures","created":"2023-02-24","cited_by_count":8,"area":null},{"id":"2410.03884","title":"KidLM: Advancing Language Models for Children -- Early Insights and Future Directions","created":"2024-10-04","cited_by_count":8,"area":null},{"id":"2210.03826","title":"An Analysis of the Effects of Decoding Algorithms on Fairness in Open-Ended Language Generation","created":"2022-10-07","cited_by_count":7,"area":null},{"id":"2504.17075","title":"Agree to Disagree? A Meta-Evaluation of LLM Misgendering","created":"2025-04-23","cited_by_count":7,"area":null},{"id":"2211.13709","title":"Undesirable Biases in NLP: Addressing Challenges of Measurement","created":"2022-11-24","cited_by_count":4,"area":null},{"id":"2502.04218","title":"Sports and Women's Sports: Gender Bias in Text Generation with Olympic Data","created":"2025-02-06","cited_by_count":3,"area":null},{"id":"2507.16557","title":"Exploring Gender Bias in Large Language Models: An In-depth Dive into the German Language","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2604.03244","title":"AI Evaluation Should Require Standardized Item-Level Data Releases","created":"2026-02-27","cited_by_count":3,"area":null},{"id":"2602.00044","title":"When LLMs Imagine People: A Human-Centered Persona Brainstorm Audit for Bias and Fairness in Creative Applications","created":"2026-01-19","cited_by_count":2,"area":null},{"id":"2507.16410","title":"GG-BBQ: German Gender Bias Benchmark for Question Answering","created":"2025-07-22","cited_by_count":1,"area":null},{"id":"2412.01711","title":"Towards Resource Efficient and Interpretable Bias Mitigation in Large Language Models","created":"2024-12-02","cited_by_count":0,"area":null},{"id":"2505.03053","title":"Developing A Framework to Support Human Evaluation of Bias in Generated Free Response Text","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2605.28848","title":"GPF-LiveNews: A Streaming Evaluation Protocol for Group-Conditioned Framing in Large Language Models","created":"2026-05-16","cited_by_count":0,"area":null}],"next_cursor":null}