TagDebias: Entity and Concept Tagging for Social Bias Mitigation in Pretrained Language Models

AbstractPre-trained language models (PLMs) play a crucial role in various applications, including sensitive domains such as the hiring process. However, extensive research has unveiled that these models tend to replicate social biases present in their pre-training data, raising ethical concerns. In this study, we propose the TagDebias method, which proposes debiasing a dataset using type tags. It then proceeds to fine-tune PLMs on this debiased dataset. Experiments show that our proposed TagDebias model, when applied to a ranking task, exhibits significant improvements in bias scores.