John vs. Ahmed: Debate-Induced Bias in Multilingual LLMs

Anastasiia Demidova, Hanin Atwany, Nour Rabih, Sanad Sha’ban, Muhammad Abdul-Mageed


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.
Anthology ID:
2024.arabicnlp-1.18
Volume:
Proceedings of The Second Arabic Natural Language Processing Conference
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Nizar Habash, Houda Bouamor, Ramy Eskander, Nadi Tomeh, Ibrahim Abu Farha, Ahmed Abdelali, Samia Touileb, Injy Hamed, Yaser Onaizan, Bashar Alhafni, Wissam Antoun, Salam Khalifa, Hatem Haddad, Imed Zitouni, Badr AlKhamissi, Rawan Almatham, Khalil Mrini
Venues:
ArabicNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
193–209
Language:
URL:
https://aclanthology.org/2024.arabicnlp-1.18
DOI:
10.18653/v1/2024.arabicnlp-1.18
Bibkey:
Cite (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.
Cite (Informal):
John vs. Ahmed: Debate-Induced Bias in Multilingual LLMs (Demidova et al., ArabicNLP-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.arabicnlp-1.18.pdf