@inproceedings{bartl-leavy-2024-showgirls,
title = "From {`}Showgirls{'} to {`}Performers{'}: Fine-tuning with Gender-inclusive Language for Bias Reduction in {LLM}s",
author = "Bartl, Marion and
Leavy, Susan",
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-1.18",
pages = "280--294",
abstract = "Gender bias is not only prevalent in Large Language Models (LLMs) and their training data, but also firmly ingrained into the structural aspects of language itself. Therefore, adapting linguistic structures within LLM training data to promote gender-inclusivity can make gender representations within the model more inclusive.The focus of our work are gender-exclusive affixes in English, such as in {`}show-girl{'} or {`}man-cave{'}, which can perpetuate gender stereotypes and binary conceptions of gender.We use an LLM training dataset to compile a catalogue of 692 gender-exclusive terms along with gender-neutral variants and from this, develop a gender-inclusive fine-tuning dataset, the {`}Tiny Heap{'}. Fine-tuning three different LLMs with this dataset, we observe an overall reduction in gender-stereotyping tendencies across the models. Our approach provides a practical method for enhancing gender inclusivity in LLM training data and contributes to incorporating queer-feminist linguistic activism in bias mitigation research in NLP.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bartl-leavy-2024-showgirls">
<titleInfo>
<title>From ‘Showgirls’ to ‘Performers’: Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marion</namePart>
<namePart type="family">Bartl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Susan</namePart>
<namePart type="family">Leavy</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>Gender bias is not only prevalent in Large Language Models (LLMs) and their training data, but also firmly ingrained into the structural aspects of language itself. Therefore, adapting linguistic structures within LLM training data to promote gender-inclusivity can make gender representations within the model more inclusive.The focus of our work are gender-exclusive affixes in English, such as in ‘show-girl’ or ‘man-cave’, which can perpetuate gender stereotypes and binary conceptions of gender.We use an LLM training dataset to compile a catalogue of 692 gender-exclusive terms along with gender-neutral variants and from this, develop a gender-inclusive fine-tuning dataset, the ‘Tiny Heap’. Fine-tuning three different LLMs with this dataset, we observe an overall reduction in gender-stereotyping tendencies across the models. Our approach provides a practical method for enhancing gender inclusivity in LLM training data and contributes to incorporating queer-feminist linguistic activism in bias mitigation research in NLP.</abstract>
<identifier type="citekey">bartl-leavy-2024-showgirls</identifier>
<location>
<url>https://aclanthology.org/2024.gebnlp-1.18</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>280</start>
<end>294</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From ‘Showgirls’ to ‘Performers’: Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMs
%A Bartl, Marion
%A Leavy, Susan
%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 bartl-leavy-2024-showgirls
%X Gender bias is not only prevalent in Large Language Models (LLMs) and their training data, but also firmly ingrained into the structural aspects of language itself. Therefore, adapting linguistic structures within LLM training data to promote gender-inclusivity can make gender representations within the model more inclusive.The focus of our work are gender-exclusive affixes in English, such as in ‘show-girl’ or ‘man-cave’, which can perpetuate gender stereotypes and binary conceptions of gender.We use an LLM training dataset to compile a catalogue of 692 gender-exclusive terms along with gender-neutral variants and from this, develop a gender-inclusive fine-tuning dataset, the ‘Tiny Heap’. Fine-tuning three different LLMs with this dataset, we observe an overall reduction in gender-stereotyping tendencies across the models. Our approach provides a practical method for enhancing gender inclusivity in LLM training data and contributes to incorporating queer-feminist linguistic activism in bias mitigation research in NLP.
%U https://aclanthology.org/2024.gebnlp-1.18
%P 280-294
Markdown (Informal)
[From ‘Showgirls’ to ‘Performers’: Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMs](https://aclanthology.org/2024.gebnlp-1.18) (Bartl & Leavy, GeBNLP-WS 2024)
ACL