@inproceedings{bergstrand-gamback-2024-detecting,
title = "Detecting and Mitigating {LGBTQIA}+ Bias in Large {N}orwegian Language Models",
author = {Bergstrand, Selma and
Gamb{\"a}ck, Bj{\"o}rn},
editor = "Fale{\'n}ska, Agnieszka and
Basta, Christine and
Costa-juss{\`a}, Marta and
Goldfarb-Tarrant, Seraphina and
Nozza, Debora",
booktitle = "Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.gebnlp-1.22",
pages = "351--364",
abstract = "The paper aims to detect and mitigate LGBTQIA+ bias in large language models (LLMs). As the usage of LLMs quickly increases, so does the significance of the harms they may cause due to bias. The research field of bias in LLMs has seen massive growth, but few attempts have been made to detect or mitigate other biases than gender bias, and most focus has been on English LLMs. This work shows experimentally that LLMs may cause representational harms towards LGBTQIA+ individuals when evaluated on sentence completion tasks and on a benchmark dataset constructed from stereotypes reported by the queer community of Norway, collected through a survey in order to directly involve the affected community. Furthermore, Norwegian training corpora are probed for queer bias, revealing strong associations between queer terms and anti-queer slurs, as well as words related to pedophilia. Finally, a fine-tuning-based debiasing method is applied to two Norwegian LLMs. This method does not consistently reduce bias, but shows that queer bias can be altered, laying the foundation for future debiasing approaches. By shedding light on the severe discrimination that can occur through the usage of LLMs, this paper contributes to the ongoing fight for equal rights for the LGBTQIA+ community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bergstrand-gamback-2024-detecting">
<titleInfo>
<title>Detecting and Mitigating LGBTQIA+ Bias in Large Norwegian Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Selma</namePart>
<namePart type="family">Bergstrand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Björn</namePart>
<namePart type="family">Gambäck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agnieszka</namePart>
<namePart type="family">Faleńska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">Basta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seraphina</namePart>
<namePart type="family">Goldfarb-Tarrant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper aims to detect and mitigate LGBTQIA+ bias in large language models (LLMs). As the usage of LLMs quickly increases, so does the significance of the harms they may cause due to bias. The research field of bias in LLMs has seen massive growth, but few attempts have been made to detect or mitigate other biases than gender bias, and most focus has been on English LLMs. This work shows experimentally that LLMs may cause representational harms towards LGBTQIA+ individuals when evaluated on sentence completion tasks and on a benchmark dataset constructed from stereotypes reported by the queer community of Norway, collected through a survey in order to directly involve the affected community. Furthermore, Norwegian training corpora are probed for queer bias, revealing strong associations between queer terms and anti-queer slurs, as well as words related to pedophilia. Finally, a fine-tuning-based debiasing method is applied to two Norwegian LLMs. This method does not consistently reduce bias, but shows that queer bias can be altered, laying the foundation for future debiasing approaches. By shedding light on the severe discrimination that can occur through the usage of LLMs, this paper contributes to the ongoing fight for equal rights for the LGBTQIA+ community.</abstract>
<identifier type="citekey">bergstrand-gamback-2024-detecting</identifier>
<location>
<url>https://aclanthology.org/2024.gebnlp-1.22</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>351</start>
<end>364</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detecting and Mitigating LGBTQIA+ Bias in Large Norwegian Language Models
%A Bergstrand, Selma
%A Gambäck, Björn
%Y Faleńska, Agnieszka
%Y Basta, Christine
%Y Costa-jussà, Marta
%Y Goldfarb-Tarrant, Seraphina
%Y Nozza, Debora
%S Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F bergstrand-gamback-2024-detecting
%X The paper aims to detect and mitigate LGBTQIA+ bias in large language models (LLMs). As the usage of LLMs quickly increases, so does the significance of the harms they may cause due to bias. The research field of bias in LLMs has seen massive growth, but few attempts have been made to detect or mitigate other biases than gender bias, and most focus has been on English LLMs. This work shows experimentally that LLMs may cause representational harms towards LGBTQIA+ individuals when evaluated on sentence completion tasks and on a benchmark dataset constructed from stereotypes reported by the queer community of Norway, collected through a survey in order to directly involve the affected community. Furthermore, Norwegian training corpora are probed for queer bias, revealing strong associations between queer terms and anti-queer slurs, as well as words related to pedophilia. Finally, a fine-tuning-based debiasing method is applied to two Norwegian LLMs. This method does not consistently reduce bias, but shows that queer bias can be altered, laying the foundation for future debiasing approaches. By shedding light on the severe discrimination that can occur through the usage of LLMs, this paper contributes to the ongoing fight for equal rights for the LGBTQIA+ community.
%U https://aclanthology.org/2024.gebnlp-1.22
%P 351-364
Markdown (Informal)
[Detecting and Mitigating LGBTQIA+ Bias in Large Norwegian Language Models](https://aclanthology.org/2024.gebnlp-1.22) (Bergstrand & Gambäck, GeBNLP-WS 2024)
ACL