General Phrase Debiaser: Debiasing Masked Language Models at a Multi-Token Level
An automatic multi-token debiasing pipeline called General Phrase Debiaser, which is capable of mitigating phrase-level biases in masked language models, and can significantly reduce gender biases on both career and multiple disciplines, across models with varying parameter sizes.
Bingkang Shi, Xiaodan Zhang, Dehan Kong et al.
· IEEE International Conferenc... · 4 citations