EMNLP 2023short findings0 citations
Intersectional Stereotypes in Large Language Models: Dataset and Analysis
Weicheng Ma, Brian Chiang, Tong Wu, Lili Wang, Soroush Vosoughi
Abstract
Despite many stereotypes targeting intersectional demographic groups, prior studies on stereotypes within Large Language Models (LLMs) primarily focus on broader, individual categories. This research bridges this gap by introducing a novel dataset of intersectional stereotypes, curated with the assistance of the ChatGPT model and manually validated. Moreover, this paper offers a comprehensive analysis of intersectional stereotype propagation in three contemporary LLMs by leveraging this dataset. The findings underscore the urgency of focusing on intersectional biases in ongoing efforts to reduce stereotype prevalence in LLMs.
Stereotype ExaminationIntersectional StereotypeDataset
BibTeX
@inproceedings{
ma2023intersectional,
title={Intersectional Stereotypes in Large Language Models: Dataset and Analysis},
author={Weicheng Ma and Brian Chiang and Tong Wu and Lili Wang and Soroush Vosoughi},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=T6GJ2Y0dn7}
}