Gender bias in transformers: A comprehensive review of detection and mitigation strategies

Nemani, Praneeth, Joel, Yericherla Deepak, Vijay, Palla and Liza, Farhana Ferdouzi ORCID: https://orcid.org/0000-0003-4854-5619 (2024) Gender bias in transformers: A comprehensive review of detection and mitigation strategies. Natural Language Processing Journal, 6. ISSN 2949-7191

Preview

PDF (Nemani_etal_2024_NLPJ) - Published Version Available under License Creative Commons Attribution. Download (1MB) | Preview

Abstract

Gender bias in artificial intelligence (AI) has emerged as a pressing concern with profound implications for individuals’ lives. This paper presents a comprehensive survey that explores gender bias in Transformer models from a linguistic perspective. While the existence of gender bias in language models has been acknowledged in previous studies, there remains a lack of consensus on how to measure and evaluate this bias effectively. Our survey critically examines the existing literature on gender bias in Transformers, shedding light on the diverse methodologies and metrics employed to assess bias. Several limitations in current approaches to measuring gender bias in Transformers are identified, encompassing the utilization of incomplete or flawed metrics, inadequate dataset sizes, and a dearth of standardization in evaluation methods. Furthermore, our survey delves into the potential ramifications of gender bias in Transformers for downstream applications, including dialogue systems and machine translation. We underscore the importance of fostering equity and fairness in these systems by emphasizing the need for heightened awareness and accountability in developing and deploying language technologies. This paper serves as a comprehensive overview of gender bias in Transformer models, providing novel insights and offering valuable directions for future research in this critical domain.

Item Type:	Article
Faculty \ School:	Faculty of Science > School of Computing Sciences
UEA Research Groups:	Faculty of Science > Research Groups > Cyber Security Privacy and Trust Laboratory Faculty of Science > Research Groups > Data Science and AI
Depositing User:	LivePure Connector
Date Deposited:	20 Dec 2023 02:58
Last Modified:	20 Dec 2024 01:10
URI:	https://ueaeprints.uea.ac.uk/id/eprint/94018
DOI:	10.1016/j.nlp.2023.100047

Downloads

Actions (login required)

View Item