Abstract
Gender bias has been widely observed in NLP models, which has the potential to perpetuate harmful stereotypes and discrimination. In this paper, we construct a dataset GenderStance of 36k samples to measure gender bias in stance detection, determining whether models consistently predict the same stance for a particular gender group. We find that all models are gender-biased and prone to classify sentences that contain male nouns as Against and those with female nouns as Favor. Moreover, extensive experiments indicate that sources of gender bias stem from the fine-tuning data and the foundation model itself. We will publicly release our code and dataset.- Anthology ID:
- 2024.findings-acl.192
- 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:
- 3229–3236
- Language:
- URL:
- https://aclanthology.org/2024.findings-acl.192
- DOI:
- 10.18653/v1/2024.findings-acl.192
- Cite (ACL):
- Yingjie Li and Yue Zhang. 2024. Pro-Woman, Anti-Man? Identifying Gender Bias in Stance Detection. In Findings of the Association for Computational Linguistics ACL 2024, pages 3229–3236, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
- Cite (Informal):
- Pro-Woman, Anti-Man? Identifying Gender Bias in Stance Detection (Li & Zhang, Findings 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2024.findings-acl.192.pdf