{"total":36,"rows":[{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2308.00755","title":"The Bias Amplification Paradox in Text-to-Image Generation","created":"2023-08-01","cited_by_count":70,"area":null},{"id":"2306.03950","title":"MISGENDERED: Limits of Large Language Models in Understanding Pronouns","created":"2023-06-06","cited_by_count":43,"area":null},{"id":"2308.02053","title":"The Unequal Opportunities of Large Language Models: Revealing Demographic Bias through Job Recommendations","created":"2023-08-03","cited_by_count":41,"area":null},{"id":"2210.10040","title":"The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks","created":"2022-10-18","cited_by_count":31,"area":null},{"id":"2306.08158","title":"Sociodemographic Bias in Language Models: A Survey and Forward Path","created":"2023-06-13","cited_by_count":28,"area":null},{"id":"2305.09022","title":"It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance","created":"2023-05-15","cited_by_count":26,"area":null},{"id":"2406.15484","title":"JobFair: A Framework for Benchmarking Gender Hiring Bias in Large Language Models","created":"2024-06-17","cited_by_count":21,"area":null},{"id":"2407.15814","title":"Perceptions of Linguistic Uncertainty by Language Models and Humans","created":"2024-07-22","cited_by_count":15,"area":null},{"id":"2410.19314","title":"Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)","created":"2024-10-25","cited_by_count":15,"area":null},{"id":"2308.12539","title":"CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model Bias","created":"2023-08-24","cited_by_count":14,"area":null},{"id":"2503.23398","title":"A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models","created":"2025-03-30","cited_by_count":14,"area":null},{"id":"2508.03712","title":"How Deep Is Representational Bias in LLMs? The Cases of Caste and Religion","created":"2025-07-22","cited_by_count":14,"area":null},{"id":"2405.00588","title":"Are Models Biased on Text without Gender-related Language?","created":"2024-05-01","cited_by_count":10,"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":"2408.12494","title":"GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models","created":"2024-08-22","cited_by_count":9,"area":null},{"id":"2409.05653","title":"WinoPron: Revisiting English Winogender Schemas for Consistency, Coverage, and Grammatical Case","created":"2024-09-09","cited_by_count":9,"area":null},{"id":"2302.07371","title":"BiasTestGPT: Using ChatGPT for Social Bias Testing of Language Models","created":"2023-02-14","cited_by_count":8,"area":null},{"id":"2305.11673","title":"Bias Beyond English: Counterfactual Tests for Bias in Sentiment Analysis in Four Languages","created":"2023-05-19","cited_by_count":8,"area":null},{"id":"2212.11672","title":"Trustworthy Social Bias Measurement","created":"2022-12-20","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":"2310.08780","title":"\"Im not Racist but...\": Discovering Bias in the Internal Knowledge of Large Language Models","created":"2023-10-13","cited_by_count":5,"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":"2311.15180","title":"Benchmarking Large Language Model Volatility","created":"2023-11-26","cited_by_count":4,"area":null},{"id":"2308.12578","title":"Mind vs. Mouth: On Measuring Re-judge Inconsistency of Social Bias in Large Language Models","created":"2023-08-24","cited_by_count":3,"area":null},{"id":"2506.04482","title":"Understanding and Meeting Practitioner Needs When Measuring Representational Harms Caused by LLM-Based Systems","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2603.23485","title":"Failure of contextual invariance in large language models","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2604.17248","title":"VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech","created":"2026-04-19","cited_by_count":3,"area":null},{"id":"2509.24468","title":"Bias Mitigation or Cultural Commonsense? Evaluating LLMs with a Japanese Dataset","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2601.12374","title":"A Scalable Entity-Based Framework for Auditing Bias in Large Language Models","created":"2026-01-18","cited_by_count":2,"area":null},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2305.12620","title":"Keeping Up with the Language Models: Systematic Benchmark Extension for Bias Auditing","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2305.12829","title":"On Bias and Fairness in NLP: Investigating the Impact of Bias and Debiasing in Language Models on the Fairness of Toxicity Detection","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2401.15499","title":"Semantic Properties of cosine based bias scores for word embeddings","created":"2024-01-27","cited_by_count":0,"area":null},{"id":"2506.23377","title":"Perspective Dial: Measuring Perspective of Text and Guiding LLM Outputs","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2509.24101","title":"BTC-SAM: Leveraging LLMs for Generation of Bias Test Cases for Sentiment Analysis Models","created":"2025-09-28","cited_by_count":0,"area":null}],"next_cursor":null}