Large language models associate Muslims with violence

被引：82

作者：

Abid, Abubakar ^{[1
]}

Farooqi, Maheen ^{[2
]}

Zou, James ^{[3
]}

机构：

[1] Stanford Univ, Dept Elect Engn, Stanford, CA 94305 USA

[2] McMaster Univ, Dept Hlth Res Methods Evidence & Impact, Hamilton, ON, Canada

[3] Stanford Univ, Dept Biomed Data Sci, Stanford, CA 94305 USA

来源：

NATURE MACHINE INTELLIGENCE | 2021年 / 3卷 / 06期

基金：

美国国家科学基金会;

关键词：

D O I：

10.1038/s42256-021-00359-2

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Large language models, which are increasingly used in AI applications, display undesirable stereotypes such as persistent associations between Muslims and violence. New approaches are needed to systematically reduce the harmful bias of language models in deployment.

引用

页码：461 / 463

页数：3