Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions

Himanshu Thakur, Atishay Jain, Praneetha Vaddamanu, Paul Pu Liang, Louis-Philippe Morency


Abstract
Societal biases present in pre-trained large language models are a critical issue as these models have been shown to propagate biases in countless downstream applications, rendering them unfair towards specific groups of people. Since large-scale retraining of these models from scratch is both time and compute-expensive, a variety of approaches have been previously proposed that de-bias a pre-trained model. While the majority of current state-of-the-art debiasing methods focus on changes to the training regime, in this paper, we propose data intervention strategies as a powerful yet simple technique to reduce gender bias in pre-trained models. Specifically, we empirically show that by fine-tuning a pre-trained model on only 10 debiased (intervened) training examples, the tendency to favor any gender is significantly reduced. Since our proposed method only needs a few training examples, we argue that our few-shot de-biasing approach is highly feasible and practical. Through extensive experimentation, we show that our de-biasing technique performs better than competitive state-of-the-art baselines with minimal loss in language modeling ability.
Anthology ID:
2023.acl-short.30
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
340–351
Language:
URL:
https://aclanthology.org/2023.acl-short.30
DOI:
10.18653/v1/2023.acl-short.30
Bibkey:
Cite (ACL):
Himanshu Thakur, Atishay Jain, Praneetha Vaddamanu, Paul Pu Liang, and Louis-Philippe Morency. 2023. Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 340–351, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions (Thakur et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2023.acl-short.30.pdf
Video:
 https://preview.aclanthology.org/improve-issue-templates/2023.acl-short.30.mp4