Theory-Grounded Measurement of U.S. Social Stereotypes in English Language Models

Yang Cao, Anna Sotnikova, Hal Daumé III, Rachel Rudinger, Linda Zou


Abstract
NLP models trained on text have been shown to reproduce human stereotypes, which can magnify harms to marginalized groups when systems are deployed at scale. We adapt the Agency-Belief-Communion (ABC) stereotype model of Koch et al. (2016) from social psychology as a framework for the systematic study and discovery of stereotypic group-trait associations in language models (LMs). We introduce the sensitivity test (SeT) for measuring stereotypical associations from language models. To evaluate SeT and other measures using the ABC model, we collect group-trait judgments from U.S.-based subjects to compare with English LM stereotypes. Finally, we extend this framework to measure LM stereotyping of intersectional identities.
Anthology ID:
2022.naacl-main.92
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1276–1295
Language:
URL:
https://aclanthology.org/2022.naacl-main.92
DOI:
10.18653/v1/2022.naacl-main.92
Bibkey:
Cite (ACL):
Yang Cao, Anna Sotnikova, Hal Daumé III, Rachel Rudinger, and Linda Zou. 2022. Theory-Grounded Measurement of U.S. Social Stereotypes in English Language Models. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1276–1295, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Theory-Grounded Measurement of U.S. Social Stereotypes in English Language Models (Cao et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.92.pdf
Code
 tristacao/u.s_stereotypes