{"total":18,"rows":[{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2307.16778","title":"KoBBQ: Korean Bias Benchmark for Question Answering","created":"2023-07-31","cited_by_count":71,"area":null},{"id":"2308.03656","title":"Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench","created":"2023-08-07","cited_by_count":54,"area":null},{"id":"2406.07243","title":"MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs","created":"2024-06-11","cited_by_count":35,"area":null},{"id":"2407.03963","title":"LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs","created":"2024-07-04","cited_by_count":33,"area":null},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2407.06957","title":"Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models","created":"2024-07-09","cited_by_count":21,"area":null},{"id":"2407.01557","title":"AI Governance and Accountability: An Analysis of Anthropic's Claude","created":"2024-05-02","cited_by_count":14,"area":null},{"id":"2408.05102","title":"How Well Do LLMs Identify Cultural Unity in Diversity?","created":"2024-08-09","cited_by_count":8,"area":null},{"id":"2508.07090","title":"BharatBBQ: A Multilingual Bias Benchmark for Question Answering in the Indian Context","created":"2025-08-09","cited_by_count":6,"area":null},{"id":"2507.09701","title":"MCEval: A Dynamic Framework for Fair Multilingual Cultural Evaluation of LLMs","created":"2025-07-13","cited_by_count":3,"area":null},{"id":"2510.05291","title":"Camellia: Benchmarking Cultural Biases in LLMs for Asian Languages","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2607.01250","title":"Structuring the Space of Sociotechnical Alignment","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2312.17256","title":"From Bytes to Biases: Investigating the Cultural Self-Perception of Large Language Models","created":"2023-12-21","cited_by_count":1,"area":null},{"id":"2503.01947","title":"Analyzing the Safety of Japanese Large Language Models in Stereotype-Triggering Prompts","created":"2025-03-03","cited_by_count":1,"area":null},{"id":"2510.04641","title":"Evaluating LLMs for Demographic-Targeted Social Bias Detection: A Comprehensive Benchmark Study","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2604.20677","title":"Intersectional Fairness in Large Language Models","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2610.14879","title":"Social Bias in Chinese Large Language Models under Social Media Expressions","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}