Data-Centric Explainable Debiasing for Improving Fairness in Pre-trained Language Models

Yingji Li, Mengnan Du, Rui Song, Xin Wang, Ying Wang


Abstract
Human-like social bias of pre-trained language models (PLMs) on downstream tasks have attracted increasing attention. The potential flaws in the training data are the main factor that causes unfairness in PLMs. Existing data-centric debiasing strategies mainly leverage explicit bias words (defined as sensitive attribute words specific to demographic groups) for counterfactual data augmentation to balance the training data. However, they lack consideration of implicit bias words potentially associated with explicit bias words in complex distribution data, which indirectly harms the fairness of PLMs. To this end, we propose a **Data**-Centric **Debias**ing method (named Data-Debias), which uses an explainability method to search for implicit bias words to assist in debiasing PLMs. Specifically, we compute the feature attributions of all tokens using the Integrated Gradients method, and then treat the tokens that have a large impact on the model’s decision as implicit bias words. To make the search results more precise, we iteratively train a biased model to amplify the bias with each iteration. Finally, we use the implicit bias words searched in the last iteration to assist in debiasing PLMs. Extensive experimental results on multiple PLMs debiasing on three different classification tasks demonstrate that Data-Debias achieves state-of-the-art debiasing performance and strong generalization while maintaining predictive abilities.
Anthology ID:
2024.findings-acl.226
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3773–3786
Language:
URL:
https://aclanthology.org/2024.findings-acl.226
DOI:
10.18653/v1/2024.findings-acl.226
Bibkey:
Cite (ACL):
Yingji Li, Mengnan Du, Rui Song, Xin Wang, and Ying Wang. 2024. Data-Centric Explainable Debiasing for Improving Fairness in Pre-trained Language Models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 3773–3786, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Data-Centric Explainable Debiasing for Improving Fairness in Pre-trained Language Models (Li et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.226.pdf