Multilingual large language models leak human stereotypes across language boundaries

Authors: Yang Trista Cao, Anna Sotnikova, Jieyu Zhao, Linda X. Zou, Rachel Rudinger, Hal Daumé III

Published: 2024

Publication: ArXiv

Research paper: Multilingual large language models leak human stereotypes across language boundaries

Institution: Microsoft Research, University of Maryland

Research Area: Multilingual Bias, Social Science, LLM, AI Bias

Discipline: Artificial Intelligence, Social Science, Large Language Models