LLMs produce racist output when prompted in African American English
成果类型：
Editorial Material
署名作者：
Blodgett, Su Lin; Talat, Zeerak
署名单位：
Mohamed bin Zayed University of Artificial Intelligence MBZUAI
刊物名称：
Nature
ISSN/ISSBN：
0028-4246
DOI：
10.1038/d41586-024-02527-x
发表日期：
2024-09-05
页码：
40-41
关键词：
摘要：
Large language models (LLMs) are becoming less overtly racist, but respond negatively to text in African American English. Such 'covert' racism could harm speakers of this dialect when LLMs are used for decision-making.