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.
@article{arxiv.2110.05367,
title = {Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting},
author = {Zahra Fatemi and Chen Xing and Wenhao Liu and Caiming Xiong},
journal= {arXiv preprint arXiv:2110.05367},
year = {2023}
}
Comments
This paper has been accepted at the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023)