Quantifying gender bias towards politicians in cross-lingual language models
PLOS ONE · 2023
DOI: 10.1371/journal.pone.0277640 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, 2023. Verfasst von Karolina Stańczak und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Copenhagen, Copenhagen, Denmark. Hauptthemen laut MEDLINE: Multilingualism, Names. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Danmarks Frie Forskningsfond.
Abstract (Originalsprache)
Recent research has demonstrated that large pre-trained language models reflect societal biases expressed in natural language. The present paper introduces a simple method for probing language models to conduct a multilingual study of gender bias towards politicians. We quantify the usage of adjectives and verbs generated by language models surrounding the names of politicians as a function of their gender. To this end, we curate a dataset of 250k politicians worldwide, including their names and gender. Our study is conducted in seven languages across six different language modeling architectures. The results demonstrate that pre-trained language models’ stance towards politicians varies strongly across analyzed languages. We find that while some words such as dead , and designated are associated with both male and female politicians, a few specific words such as beautiful and divorced are predominantly associated with female politicians. Finally, and contrary to previous findings, our study suggests that larger language models do not tend to be significantly more gender-biased than smaller ones.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.
- Department of Computer Science and Technology, University of Cambridge, Cambridge, United Kingdom.
- Department of Computer Science, ETH Zürich, Zürich, Switzerland.
ORCID-Profile: Karolina Stańczak
Förderung
- Danmarks Frie Forskningsfond
Zitieren
APA
Stańczak, K., Ray Choudhury, S., Pimentel, T., Cotterell, R., & Augenstein, I. (2023). Quantifying gender bias towards politicians in cross-lingual language models. PLOS ONE. https://doi.org/10.1371/journal.pone.0277640
Vancouver
Stańczak K, Ray Choudhury S, Pimentel T, Cotterell R, Augenstein I. Quantifying gender bias towards politicians in cross-lingual language models. PLOS ONE. 2023. doi:10.1371/journal.pone.0277640
BibTeX
@article{Staczak2023,
author = {Stańczak, Karolina and Ray Choudhury, Sagnik and Pimentel, Tiago and Cotterell, Ryan and Augenstein, Isabelle},
title = {Quantifying gender bias towards politicians in cross-lingual language models},
journal = {PLOS ONE},
year = {2023},
doi = {10.1371/journal.pone.0277640}
}
EUVIMED