Abstract
Existing studies addressing gender bias of pre-trained language models, usually build a small gender-neutral data set and conduct a second phase pre-training on the model with such data. However, given the limited size and concentrated focus of the gender-neutral data, catastrophic forgetting would occur during second-phase pre-training. Forgetting information in the original training data may damage the model’s downstream performance by a large margin. In this work, we empirically show that catastrophic forgetting occurs in such methods by evaluating them with general NLP tasks in GLUE. Then, we propose a new method, GEnder Equality Prompt (GEEP), to improve gender fairness of pre-trained models with less forgetting. GEEP freezes the pre-trained model and learns gender-related prompts with gender-neutral data. Empirical results show that GEEP not only achieves SOTA performances on gender fairness tasks, but also forgets less and performs better on GLUE by a large margin.- Anthology ID:
- 2023.acl-short.108
- 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:
- 1249–1262
- Language:
- URL:
- https://aclanthology.org/2023.acl-short.108
- DOI:
- 10.18653/v1/2023.acl-short.108
- Cite (ACL):
- Zahra Fatemi, Chen Xing, Wenhao Liu, and Caimming Xiong. 2023. Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1249–1262, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting (Fatemi et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2023.acl-short.108.pdf