Sociodemographic Bias in Language Models: A Survey and Forward Path

Sociodemographic bias in language models (LMs) has the potential for harm when deployed in real-world settings. This paper presents a comprehensive survey of the past decade of research on sociodemographic bias in LMs, organized into a typology that facilitates examining the different aims: types of...

Full description

Saved in:
Bibliographic Details
Main Authors Gupta, Vipul, Venkit, Pranav Narayanan, Wilson, Shomir, Passonneau, Rebecca J
Format Journal Article
LanguageEnglish
Published 13.06.2023
Subjects
Computer Science - Artificial Intelligence
Computer Science - Computation and Language
Computer Science - Learning
Online AccessGet full text

Cover

More Information
Summary:Sociodemographic bias in language models (LMs) has the potential for harm when deployed in real-world settings. This paper presents a comprehensive survey of the past decade of research on sociodemographic bias in LMs, organized into a typology that facilitates examining the different aims: types of bias, quantifying bias, and debiasing techniques. We track the evolution of the latter two questions, then identify current trends and their limitations, as well as emerging techniques. To guide future research towards more effective and reliable solutions, and to help authors situate their work within this broad landscape, we conclude with a checklist of open questions.
DOI:10.48550/arxiv.2306.08158