Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal

Umang Gupta, Jwala Dhamala, Varun Kumar, Apurv Verma, Yada Pruksachatkun, Satyapriya Krishna, Rahul Gupta, Kai-Wei Chang, Greg Ver Steeg, Aram Galstyan


Abstract
Language models excel at generating coherent text, and model compression techniques such as knowledge distillation have enabled their use in resource-constrained settings. However, these models can be biased in multiple ways, including the unfounded association of male and female genders with gender-neutral professions. Therefore, knowledge distillation without any fairness constraints may preserve or exaggerate the teacher model’s biases onto the distilled model. To this end, we present a novel approach to mitigate gender disparity in text generation by learning a fair model during knowledge distillation. We propose two modifications to the base knowledge distillation based on counterfactual role reversal—modifying teacher probabilities and augmenting the training set. We evaluate gender polarity across professions in open-ended text generated from the resulting distilled and finetuned GPT–2 models and demonstrate a substantial reduction in gender disparity with only a minor compromise in utility. Finally, we observe that language models that reduce gender polarity in language generation do not improve embedding fairness or downstream classification fairness.
Anthology ID:
2022.findings-acl.55
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
658–678
Language:
URL:
https://aclanthology.org/2022.findings-acl.55
DOI:
10.18653/v1/2022.findings-acl.55
Bibkey:
Cite (ACL):
Umang Gupta, Jwala Dhamala, Varun Kumar, Apurv Verma, Yada Pruksachatkun, Satyapriya Krishna, Rahul Gupta, Kai-Wei Chang, Greg Ver Steeg, and Aram Galstyan. 2022. Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal. In Findings of the Association for Computational Linguistics: ACL 2022, pages 658–678, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal (Gupta et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-acl.55.pdf
Data
WebText