Upstream Mitigation Is Not All You Need: Testing the Bias Transfer Hypothesis in Pre-Trained Language Models

Ryan Steed, Swetasudha Panda, Ari Kobren, Michael Wick


Abstract
A few large, homogenous, pre-trained models undergird many machine learning systems — and often, these models contain harmful stereotypes learned from the internet. We investigate the bias transfer hypothesis: the theory that social biases (such as stereotypes) internalized by large language models during pre-training transfer into harmful task-specific behavior after fine-tuning. For two classification tasks, we find that reducing intrinsic bias with controlled interventions before fine-tuning does little to mitigate the classifier’s discriminatory behavior after fine-tuning. Regression analysis suggests that downstream disparities are better explained by biases in the fine-tuning dataset. Still, pre-training plays a role: simple alterations to co-occurrence rates in the fine-tuning dataset are ineffective when the model has been pre-trained. Our results encourage practitioners to focus more on dataset quality and context-specific harms.
Anthology ID:
2022.acl-long.247
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3524–3542
Language:
URL:
https://aclanthology.org/2022.acl-long.247
DOI:
10.18653/v1/2022.acl-long.247
Bibkey:
Cite (ACL):
Ryan Steed, Swetasudha Panda, Ari Kobren, and Michael Wick. 2022. Upstream Mitigation Is Not All You Need: Testing the Bias Transfer Hypothesis in Pre-Trained Language Models. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3524–3542, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Upstream Mitigation Is Not All You Need: Testing the Bias Transfer Hypothesis in Pre-Trained Language Models (Steed et al., ACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2022.acl-long.247.pdf
Software:
 2022.acl-long.247.software.zip