Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting
Zahra Fatemi, Xing Chen, Wenhao Liu, Caimming Xiong · 2023
Existing studies addressing gender bias of pretrained 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 secondphase 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 genderneutral 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.