Adversarial Examples Generation for Reducing Implicit Gender Bias in Pre-trained Models
This addresses gender bias in NLP models, which is a critical issue for fairness in practical applications, though it appears incremental by focusing on sentence-level and implicit cases.
The paper tackled the problem of implicit gender bias in pre-trained language models by proposing a method to automatically generate sentence-level adversarial examples and a metric to measure bias, with results evaluated in terms of accuracy.
Over the last few years, Contextualized Pre-trained Neural Language Models, such as BERT, GPT, have shown significant gains in various NLP tasks. To enhance the robustness of existing pre-trained models, one way is adversarial examples generation and evaluation for conducting data augmentation or adversarial learning. In the meanwhile, gender bias embedded in the models seems to be a serious problem in practical applications. Many researches have covered the gender bias produced by word-level information(e.g. gender-stereotypical occupations), while few researchers have investigated the sentence-level cases and implicit cases. In this paper, we proposed a method to automatically generate implicit gender bias samples at sentence-level and a metric to measure gender bias. Samples generated by our method will be evaluated in terms of accuracy. The metric will be used to guide the generation of examples from Pre-trained models. Therefore, those examples could be used to impose attacks on Pre-trained Models. Finally, we discussed the evaluation efficacy of our generated examples on reducing gender bias for future research.