@inproceedings{demidova-etal-2024-john,
title = "John vs. Ahmed: Debate-Induced Bias in Multilingual {LLM}s",
author = "Demidova, Anastasiia and
Atwany, Hanin and
Rabih, Nour and
Sha{'}ban, Sanad and
Abdul-Mageed, Muhammad",
editor = "Habash, Nizar and
Bouamor, Houda and
Eskander, Ramy and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Abdelali, Ahmed and
Touileb, Samia and
Hamed, Injy and
Onaizan, Yaser and
Alhafni, Bashar and
Antoun, Wissam and
Khalifa, Salam and
Haddad, Hatem and
Zitouni, Imed and
AlKhamissi, Badr and
Almatham, Rawan and
Mrini, Khalil",
booktitle = "Proceedings of The Second Arabic Natural Language Processing Conference",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.arabicnlp-1.18",
pages = "193--209",
abstract = "Large language models (LLMs) play a crucial role in a wide range of real world applications. However, concerns about their safety and ethical implications are growing. While research on LLM safety is expanding, there is a noticeable gap in evaluating safety across multiple languages, especially in Arabic and Russian. We address this gap by exploring biases in LLMs across different languages and contexts, focusing on GPT-3.5 and Gemini. Through carefully designed argument-based prompts and scenarios in Arabic, English, and Russian, we examine biases in cultural, political, racial, religious, and gender domains. Our findings reveal biases in these domains. In particular, our investigation uncovers subtle biases where each model tends to present winners as those speaking the primary language the model is prompted with. Our study contributes to ongoing efforts to ensure justice and equality in LLM development and emphasizes the importance of further research towards responsible progress in this field.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="demidova-etal-2024-john">
<titleInfo>
<title>John vs. Ahmed: Debate-Induced Bias in Multilingual LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anastasiia</namePart>
<namePart type="family">Demidova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanin</namePart>
<namePart type="family">Atwany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nour</namePart>
<namePart type="family">Rabih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanad</namePart>
<namePart type="family">Sha’ban</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</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 Second Arabic Natural Language Processing Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramy</namePart>
<namePart type="family">Eskander</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Touileb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wissam</namePart>
<namePart type="family">Antoun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatem</namePart>
<namePart type="family">Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Badr</namePart>
<namePart type="family">AlKhamissi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</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>Large language models (LLMs) play a crucial role in a wide range of real world applications. However, concerns about their safety and ethical implications are growing. While research on LLM safety is expanding, there is a noticeable gap in evaluating safety across multiple languages, especially in Arabic and Russian. We address this gap by exploring biases in LLMs across different languages and contexts, focusing on GPT-3.5 and Gemini. Through carefully designed argument-based prompts and scenarios in Arabic, English, and Russian, we examine biases in cultural, political, racial, religious, and gender domains. Our findings reveal biases in these domains. In particular, our investigation uncovers subtle biases where each model tends to present winners as those speaking the primary language the model is prompted with. Our study contributes to ongoing efforts to ensure justice and equality in LLM development and emphasizes the importance of further research towards responsible progress in this field.</abstract>
<identifier type="citekey">demidova-etal-2024-john</identifier>
<location>
<url>https://aclanthology.org/2024.arabicnlp-1.18</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>193</start>
<end>209</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T John vs. Ahmed: Debate-Induced Bias in Multilingual LLMs
%A Demidova, Anastasiia
%A Atwany, Hanin
%A Rabih, Nour
%A Sha’ban, Sanad
%A Abdul-Mageed, Muhammad
%Y Habash, Nizar
%Y Bouamor, Houda
%Y Eskander, Ramy
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Abdelali, Ahmed
%Y Touileb, Samia
%Y Hamed, Injy
%Y Onaizan, Yaser
%Y Alhafni, Bashar
%Y Antoun, Wissam
%Y Khalifa, Salam
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y AlKhamissi, Badr
%Y Almatham, Rawan
%Y Mrini, Khalil
%S Proceedings of The Second Arabic Natural Language Processing Conference
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F demidova-etal-2024-john
%X Large language models (LLMs) play a crucial role in a wide range of real world applications. However, concerns about their safety and ethical implications are growing. While research on LLM safety is expanding, there is a noticeable gap in evaluating safety across multiple languages, especially in Arabic and Russian. We address this gap by exploring biases in LLMs across different languages and contexts, focusing on GPT-3.5 and Gemini. Through carefully designed argument-based prompts and scenarios in Arabic, English, and Russian, we examine biases in cultural, political, racial, religious, and gender domains. Our findings reveal biases in these domains. In particular, our investigation uncovers subtle biases where each model tends to present winners as those speaking the primary language the model is prompted with. Our study contributes to ongoing efforts to ensure justice and equality in LLM development and emphasizes the importance of further research towards responsible progress in this field.
%U https://aclanthology.org/2024.arabicnlp-1.18
%P 193-209
Markdown (Informal)
[John vs. Ahmed: Debate-Induced Bias in Multilingual LLMs](https://aclanthology.org/2024.arabicnlp-1.18) (Demidova et al., ArabicNLP-WS 2024)
ACL
- Anastasiia Demidova, Hanin Atwany, Nour Rabih, Sanad Sha’ban, and Muhammad Abdul-Mageed. 2024. John vs. Ahmed: Debate-Induced Bias in Multilingual LLMs. In Proceedings of The Second Arabic Natural Language Processing Conference, pages 193–209, Bangkok, Thailand. Association for Computational Linguistics.