GeWu: A Culturally-Grounded Chinese Benchmark for Multi-Stage Social Bias Evaluation in Large Language Models

Yi Lin, Ziyi Zhou, Jiashi Gao, Xinwei Guo, Jiaxin Zhang 0007, Haiyan Wu, Xin Yao 0001, Xuetao Wei. GeWu: A Culturally-Grounded Chinese Benchmark for Multi-Stage Social Bias Evaluation in Large Language Models. In Sven Koenig, Chad Jenkins, Matthew E. Taylor, editors, Fortieth AAAI Conference on Artificial Intelligence, Thirty-Eighth Conference on Innovative Applications of Artificial Intelligence, Sixteenth Symposium on Educational Advances in Artificial Intelligence, AAAI 2026, Singapore, January 20-27, 2026. pages 32033-32041, AAAI Press, 2026. [doi]

Abstract

Abstract is missing.