More than Minorities and Majorities: Understanding Multilateral Bias in Language Generation
Jiaxu Zhao, Zijing Shi, Yitong Li, Yulong Pei, Ling Chen, Meng Fang, Mykola Pechenizkiy
Abstract
Pretrained models learned from real corpora can often capture undesirable features, leading to bias issues against different demographic groups. Most existing studies on bias dataset construction or bias mitigation methods only focus on one demographic group pair to study a certain bias, e.g. black vs. white for racial bias. However, in real-world applications, there are more than two demographic groups that are at risk of the same bias. In this paper, we propose to analyze and reduce biases across multiple demographic groups. We collect and build a multi-demographic bias dataset including five commonly discussed bias dimensions. To mitigate multi-demographic bias, we adopt several novel debiasing methods, including regularisation-based and augmentation-based methods, as well as appropriate evaluation metrics for multi-demographic bias measurement. Experimental results on the proposed multi-demographic dataset show that a fairer model can be achieved using a multi-demographic debiasing approach. Also, the model debiased using the proposed multi-demographic debiasing methods can better transfer to unseen demographics without sacrificing the performance of the pretrained model.- Anthology ID:
- 2024.findings-acl.594
- Volume:
- Findings of the Association for Computational Linguistics ACL 2024
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand and virtual meeting
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 9987–10001
- Language:
- URL:
- https://aclanthology.org/2024.findings-acl.594
- DOI:
- Cite (ACL):
- Jiaxu Zhao, Zijing Shi, Yitong Li, Yulong Pei, Ling Chen, Meng Fang, and Mykola Pechenizkiy. 2024. More than Minorities and Majorities: Understanding Multilateral Bias in Language Generation. In Findings of the Association for Computational Linguistics ACL 2024, pages 9987–10001, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
- Cite (Informal):
- More than Minorities and Majorities: Understanding Multilateral Bias in Language Generation (Zhao et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.findings-acl.594.pdf