General Phrase Debiaser: Debiasing Masked Language Models at a Multi-Token Level

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shi, Bingkang, Zhang, Xiaodan, Kong, Dehan, Wu, Yulei, Liu, Zongzhen, Lyu, Honglei, Huang, Longtao
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916105275047936
author Shi, Bingkang
Zhang, Xiaodan
Kong, Dehan
Wu, Yulei
Liu, Zongzhen
Lyu, Honglei
Huang, Longtao
author_facet Shi, Bingkang
Zhang, Xiaodan
Kong, Dehan
Wu, Yulei
Liu, Zongzhen
Lyu, Honglei
Huang, Longtao
contents The social biases and unwelcome stereotypes revealed by pretrained language models are becoming obstacles to their application. Compared to numerous debiasing methods targeting word level, there has been relatively less attention on biases present at phrase level, limiting the performance of debiasing in discipline domains. In this paper, we propose an automatic multi-token debiasing pipeline called \textbf{General Phrase Debiaser}, which is capable of mitigating phrase-level biases in masked language models. Specifically, our method consists of a \textit{phrase filter stage} that generates stereotypical phrases from Wikipedia pages as well as a \textit{model debias stage} that can debias models at the multi-token level to tackle bias challenges on phrases. The latter searches for prompts that trigger model's bias, and then uses them for debiasing. State-of-the-art results on standard datasets and metrics show that our approach can significantly reduce gender biases on both career and multiple disciplines, across models with varying parameter sizes.
format Preprint
id arxiv_https___arxiv_org_abs_2311_13892
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle General Phrase Debiaser: Debiasing Masked Language Models at a Multi-Token Level
Shi, Bingkang
Zhang, Xiaodan
Kong, Dehan
Wu, Yulei
Liu, Zongzhen
Lyu, Honglei
Huang, Longtao
Computation and Language
Artificial Intelligence
The social biases and unwelcome stereotypes revealed by pretrained language models are becoming obstacles to their application. Compared to numerous debiasing methods targeting word level, there has been relatively less attention on biases present at phrase level, limiting the performance of debiasing in discipline domains. In this paper, we propose an automatic multi-token debiasing pipeline called \textbf{General Phrase Debiaser}, which is capable of mitigating phrase-level biases in masked language models. Specifically, our method consists of a \textit{phrase filter stage} that generates stereotypical phrases from Wikipedia pages as well as a \textit{model debias stage} that can debias models at the multi-token level to tackle bias challenges on phrases. The latter searches for prompts that trigger model's bias, and then uses them for debiasing. State-of-the-art results on standard datasets and metrics show that our approach can significantly reduce gender biases on both career and multiple disciplines, across models with varying parameter sizes.
title General Phrase Debiaser: Debiasing Masked Language Models at a Multi-Token Level
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2311.13892