Visual Exploration of Indirect Bias in Language Models

Loading...
Thumbnail Image
Date
2023
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Language models are trained on large text corpora that often include stereotypes. This can lead to direct or indirect bias in downstream applications. In this work, we present a method for interactive visual exploration of indirect multiclass bias learned by contextual word embeddings. We introduce a new indirect bias quantification score and present two interactive visualizations to explore interactions between multiple non-sensitive concepts (such as sports, occupations, and beverages) and sensitive attributes (such as gender or year of birth) based on this score.
Description

CCS Concepts: Human-centered computing -> Visual analytics; Computing methodologies -> Natural language processing

        
@inproceedings{
10.2312:evs.20231034
, booktitle = {
EuroVis 2023 - Short Papers
}, editor = {
Hoellt, Thomas
and
Aigner, Wolfgang
and
Wang, Bei
}, title = {{
Visual Exploration of Indirect Bias in Language Models
}}, author = {
Louis-Alexandre, Judith
and
Waldner, Manuela
}, year = {
2023
}, publisher = {
The Eurographics Association
}, ISBN = {
978-3-03868-219-6
}, DOI = {
10.2312/evs.20231034
} }
Citation
Collections