Abstract
BERT-like language models (LMs), when exposed to large unstructured datasets, are known to learn and sometimes even amplify the biases present in such data. These biases generally reflect social stereotypes with respect to gender, race, age, and others. In this paper, we analyze the variations in gender and racial biases in BERT, a large pre-trained LM, when exposed to different demographic groups. Specifically, we investigate the effect of fine-tuning BERT on text authored by historically disadvantaged demographic groups in comparison to that by advantaged groups. We show that simply by fine-tuning BERT-like LMs on text authored by certain demographic groups can result in the mitigation of social biases in these LMs against various target groups.- Anthology ID:
- 2022.aacl-short.38
- Volume:
- Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
- Month:
- November
- Year:
- 2022
- Address:
- Online only
- Editors:
- Yulan He, Heng Ji, Sujian Li, Yang Liu, Chua-Hui Chang
- Venues:
- AACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 311–319
- Language:
- URL:
- https://aclanthology.org/2022.aacl-short.38
- DOI:
- Cite (ACL):
- Aparna Garimella, Rada Mihalcea, and Akhash Amarnath. 2022. Demographic-Aware Language Model Fine-tuning as a Bias Mitigation Technique. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 311–319, Online only. Association for Computational Linguistics.
- Cite (Informal):
- Demographic-Aware Language Model Fine-tuning as a Bias Mitigation Technique (Garimella et al., AACL-IJCNLP 2022)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2022.aacl-short.38.pdf