CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models

Nikita Nangia, Clara Vania, Rasika Bhalerao, Samuel R. Bowman


Abstract
Pretrained language models, especially masked language models (MLMs) have seen success across many NLP tasks. However, there is ample evidence that they use the cultural biases that are undoubtedly present in the corpora they are trained on, implicitly creating harm with biased representations. To measure some forms of social bias in language models against protected demographic groups in the US, we introduce the Crowdsourced Stereotype Pairs benchmark (CrowS-Pairs). CrowS-Pairs has 1508 examples that cover stereotypes dealing with nine types of bias, like race, religion, and age. In CrowS-Pairs a model is presented with two sentences: one that is more stereotyping and another that is less stereotyping. The data focuses on stereotypes about historically disadvantaged groups and contrasts them with advantaged groups. We find that all three of the widely-used MLMs we evaluate substantially favor sentences that express stereotypes in every category in CrowS-Pairs. As work on building less biased models advances, this dataset can be used as a benchmark to evaluate progress.
Anthology ID:
2020.emnlp-main.154
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1953–1967
Language:
URL:
https://aclanthology.org/2020.emnlp-main.154
DOI:
10.18653/v1/2020.emnlp-main.154
Bibkey:
Cite (ACL):
Nikita Nangia, Clara Vania, Rasika Bhalerao, and Samuel R. Bowman. 2020. CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1953–1967, Online. Association for Computational Linguistics.
Cite (Informal):
CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models (Nangia et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2020.emnlp-main.154.pdf
Optional supplementary material:
 2020.emnlp-main.154.OptionalSupplementaryMaterial.zip
Video:
 https://slideslive.com/38939165
Code
 nyu-mll/crows-pairs
Data
CrowS-PairsRACEStereoSetWinoBias