@inproceedings{fridriksdottir-einarsson-2024-gendered,
title = "Gendered Grammar or Ingrained Bias? Exploring Gender Bias in {I}celandic Language Models",
author = "Fri{\dh}riksd{\'o}ttir, Steinunn Rut and
Einarsson, Hafsteinn",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.671",
pages = "7596--7610",
abstract = "Large language models, trained on vast datasets, exhibit increased output quality in proportion to the amount of data that is used to train them. This data-driven learning process has brought forth a pressing issue where these models may not only reflect but also amplify gender bias, racism, religious prejudice, and queerphobia present in their training data that may not always be recent. This study explores gender bias in language models trained on Icelandic, focusing on occupation-related terms. Icelandic is a highly grammatically gendered language that favors the masculine when referring to groups of people with indeterminable genders. Our aim is to explore whether language models merely mirror gender distributions within the corresponding professions or if they exhibit biases tied to their grammatical genders. Results indicate a significant overall predisposition towards the masculine but specific occupation terms consistently lean toward a particular gender, indicating complex interplays of societal and linguistic influences.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fridriksdottir-einarsson-2024-gendered">
<titleInfo>
<title>Gendered Grammar or Ingrained Bias? Exploring Gender Bias in Icelandic Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Steinunn</namePart>
<namePart type="given">Rut</namePart>
<namePart type="family">Fri\dhriksdóttir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hafsteinn</namePart>
<namePart type="family">Einarsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models, trained on vast datasets, exhibit increased output quality in proportion to the amount of data that is used to train them. This data-driven learning process has brought forth a pressing issue where these models may not only reflect but also amplify gender bias, racism, religious prejudice, and queerphobia present in their training data that may not always be recent. This study explores gender bias in language models trained on Icelandic, focusing on occupation-related terms. Icelandic is a highly grammatically gendered language that favors the masculine when referring to groups of people with indeterminable genders. Our aim is to explore whether language models merely mirror gender distributions within the corresponding professions or if they exhibit biases tied to their grammatical genders. Results indicate a significant overall predisposition towards the masculine but specific occupation terms consistently lean toward a particular gender, indicating complex interplays of societal and linguistic influences.</abstract>
<identifier type="citekey">fridriksdottir-einarsson-2024-gendered</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.671</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>7596</start>
<end>7610</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Gendered Grammar or Ingrained Bias? Exploring Gender Bias in Icelandic Language Models
%A Fri\dhriksdóttir, Steinunn Rut
%A Einarsson, Hafsteinn
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F fridriksdottir-einarsson-2024-gendered
%X Large language models, trained on vast datasets, exhibit increased output quality in proportion to the amount of data that is used to train them. This data-driven learning process has brought forth a pressing issue where these models may not only reflect but also amplify gender bias, racism, religious prejudice, and queerphobia present in their training data that may not always be recent. This study explores gender bias in language models trained on Icelandic, focusing on occupation-related terms. Icelandic is a highly grammatically gendered language that favors the masculine when referring to groups of people with indeterminable genders. Our aim is to explore whether language models merely mirror gender distributions within the corresponding professions or if they exhibit biases tied to their grammatical genders. Results indicate a significant overall predisposition towards the masculine but specific occupation terms consistently lean toward a particular gender, indicating complex interplays of societal and linguistic influences.
%U https://aclanthology.org/2024.lrec-main.671
%P 7596-7610
Markdown (Informal)
[Gendered Grammar or Ingrained Bias? Exploring Gender Bias in Icelandic Language Models](https://aclanthology.org/2024.lrec-main.671) (Friðriksdóttir & Einarsson, LREC-COLING 2024)
ACL