NAACL 2024findings0 citations
TagDebias: Entity and Concept Tagging for Social Bias Mitigation in Pretrained Language Models
Abstract
Pre-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.
BibTeX
@inproceedings{moslemi-zouaq-2024-tagdebias,
title = "{T}ag{D}ebias: Entity and Concept Tagging for Social Bias Mitigation in Pretrained Language Models",
author = "Moslemi, Mehrnaz and
Zouaq, Amal",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.101/",
doi = "10.18653/v1/2024.findings-naacl.101",
pages = "1553--1567"
}