Projective Methods for Mitigating Gender Bias in Pre-trained Language Models
Hillary Dawkins, Isar Nejadgholi, Daniel Gillis, Judi McCuaig
Abstract
Mitigation of gender bias in NLP has a long history tied to debiasing static word embeddings. More recently, attention has shifted to debiasing pre-trained language models. We study to what extent the simplest projective debiasing methods, developed for word embeddings, can help when applied to BERT’s internal representations. Projective methods are fast to implement, use a small number of saved parameters, and make no updates to the existing model parameters. We evaluate the efficacy of the methods in reducing both intrinsic bias, as measured by BERT’s next sentence prediction task, and in mitigating observed bias in a downstream setting when fine-tuned. To this end, we also provide a critical analysis of a popular gender-bias assessment test for quantifying intrinsic bias, resulting in an enhanced test set and new bias measures. We find that projective methods can be effective at both intrinsic bias and downstream bias mitigation, but that the two outcomes are not necessarily correlated. This finding serves as a warning that intrinsic bias test sets, based either on language modeling tasks or next sentence prediction, should not be the only benchmark in developing a debiased language model.- Anthology ID:
- 2024.lrec-main.1146
- Volume:
- Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
- Venues:
- LREC | COLING
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 13079–13091
- Language:
- URL:
- https://aclanthology.org/2024.lrec-main.1146
- DOI:
- Cite (ACL):
- Hillary Dawkins, Isar Nejadgholi, Daniel Gillis, and Judi McCuaig. 2024. Projective Methods for Mitigating Gender Bias in Pre-trained Language Models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 13079–13091, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- Projective Methods for Mitigating Gender Bias in Pre-trained Language Models (Dawkins et al., LREC-COLING 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.lrec-main.1146.pdf