@inproceedings{nie-etal-2024-multilingual,
title = "Do Multilingual Large Language Models Mitigate Stereotype Bias?",
author = {Nie, Shangrui and
Fromm, Michael and
Welch, Charles and
G{\"o}rge, Rebekka and
Karimi, Akbar and
Plepi, Joan and
Mowmita, Nazia and
Flores-Herr, Nicolas and
Ali, Mehdi and
Flek, Lucie},
editor = "Prabhakaran, Vinodkumar and
Dev, Sunipa and
Benotti, Luciana and
Hershcovich, Daniel and
Cabello, Laura and
Cao, Yong and
Adebara, Ife and
Zhou, Li",
booktitle = "Proceedings of the 2nd Workshop on Cross-Cultural Considerations in NLP",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.c3nlp-1.6",
doi = "10.18653/v1/2024.c3nlp-1.6",
pages = "65--83",
abstract = "While preliminary findings indicate that multilingual LLMs exhibit reduced bias compared to monolingual ones, a comprehensive understanding of the effect of multilingual training on bias mitigation, is lacking. This study addresses this gap by systematically training six LLMs of identical size (2.6B parameters) and architecture: five monolingual models (English, German, French, Italian, and Spanish) and one multilingual model trained on an equal distribution of data across these languages, all using publicly available data. To ensure robust evaluation, standard bias benchmarks were automatically translated into the five target languages and verified for both translation quality and bias preservation by human annotators. Our results consistently demonstrate that multilingual training effectively mitigates bias. Moreover, we observe that multilingual models achieve not only lower bias but also superior prediction accuracy when compared to monolingual models with the same amount of training data, model architecture, and size.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nie-etal-2024-multilingual">
<titleInfo>
<title>Do Multilingual Large Language Models Mitigate Stereotype Bias?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shangrui</namePart>
<namePart type="family">Nie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Fromm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charles</namePart>
<namePart type="family">Welch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebekka</namePart>
<namePart type="family">Görge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akbar</namePart>
<namePart type="family">Karimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joan</namePart>
<namePart type="family">Plepi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nazia</namePart>
<namePart type="family">Mowmita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Flores-Herr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehdi</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucie</namePart>
<namePart type="family">Flek</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 2nd Workshop on Cross-Cultural Considerations in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vinodkumar</namePart>
<namePart type="family">Prabhakaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luciana</namePart>
<namePart type="family">Benotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Hershcovich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Cabello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ife</namePart>
<namePart type="family">Adebara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Zhou</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>While preliminary findings indicate that multilingual LLMs exhibit reduced bias compared to monolingual ones, a comprehensive understanding of the effect of multilingual training on bias mitigation, is lacking. This study addresses this gap by systematically training six LLMs of identical size (2.6B parameters) and architecture: five monolingual models (English, German, French, Italian, and Spanish) and one multilingual model trained on an equal distribution of data across these languages, all using publicly available data. To ensure robust evaluation, standard bias benchmarks were automatically translated into the five target languages and verified for both translation quality and bias preservation by human annotators. Our results consistently demonstrate that multilingual training effectively mitigates bias. Moreover, we observe that multilingual models achieve not only lower bias but also superior prediction accuracy when compared to monolingual models with the same amount of training data, model architecture, and size.</abstract>
<identifier type="citekey">nie-etal-2024-multilingual</identifier>
<identifier type="doi">10.18653/v1/2024.c3nlp-1.6</identifier>
<location>
<url>https://aclanthology.org/2024.c3nlp-1.6</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>65</start>
<end>83</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do Multilingual Large Language Models Mitigate Stereotype Bias?
%A Nie, Shangrui
%A Fromm, Michael
%A Welch, Charles
%A Görge, Rebekka
%A Karimi, Akbar
%A Plepi, Joan
%A Mowmita, Nazia
%A Flores-Herr, Nicolas
%A Ali, Mehdi
%A Flek, Lucie
%Y Prabhakaran, Vinodkumar
%Y Dev, Sunipa
%Y Benotti, Luciana
%Y Hershcovich, Daniel
%Y Cabello, Laura
%Y Cao, Yong
%Y Adebara, Ife
%Y Zhou, Li
%S Proceedings of the 2nd Workshop on Cross-Cultural Considerations in NLP
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F nie-etal-2024-multilingual
%X While preliminary findings indicate that multilingual LLMs exhibit reduced bias compared to monolingual ones, a comprehensive understanding of the effect of multilingual training on bias mitigation, is lacking. This study addresses this gap by systematically training six LLMs of identical size (2.6B parameters) and architecture: five monolingual models (English, German, French, Italian, and Spanish) and one multilingual model trained on an equal distribution of data across these languages, all using publicly available data. To ensure robust evaluation, standard bias benchmarks were automatically translated into the five target languages and verified for both translation quality and bias preservation by human annotators. Our results consistently demonstrate that multilingual training effectively mitigates bias. Moreover, we observe that multilingual models achieve not only lower bias but also superior prediction accuracy when compared to monolingual models with the same amount of training data, model architecture, and size.
%R 10.18653/v1/2024.c3nlp-1.6
%U https://aclanthology.org/2024.c3nlp-1.6
%U https://doi.org/10.18653/v1/2024.c3nlp-1.6
%P 65-83
Markdown (Informal)
[Do Multilingual Large Language Models Mitigate Stereotype Bias?](https://aclanthology.org/2024.c3nlp-1.6) (Nie et al., C3NLP-WS 2024)
ACL
- Shangrui Nie, Michael Fromm, Charles Welch, Rebekka Görge, Akbar Karimi, Joan Plepi, Nazia Mowmita, Nicolas Flores-Herr, Mehdi Ali, and Lucie Flek. 2024. Do Multilingual Large Language Models Mitigate Stereotype Bias?. In Proceedings of the 2nd Workshop on Cross-Cultural Considerations in NLP, pages 65–83, Bangkok, Thailand. Association for Computational Linguistics.