@inproceedings{magdy-etal-2025-jawaher,
title = "{JAWAHER}: A Multidialectal Dataset of {A}rabic Proverbs for {LLM} Benchmarking",
author = "Magdy, Samar Mohamed and
Kwon, Sang Yun and
Alwajih, Fakhraddin and
Abdelfadil, Safaa Taher and
Shehata, Shady and
Abdul-Mageed, Muhammad",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.613/",
doi = "10.18653/v1/2025.naacl-long.613",
pages = "12320--12341",
ISBN = "979-8-89176-189-6",
abstract = "Recent advancements in instruction fine-tuning, alignment methods such as reinforcement learning from human feedback (RLHF), and optimization techniques like direct preference optimization (DPO), have significantly enhanced the adaptability of large language models (LLMs) to user preferences. However, despite these innovations, many LLMs continue to exhibit biases toward Western, Anglo-centric, or American cultures, with performance on English data consistently surpassing that of other languages. This reveals a persistent cultural gap in LLMs, which complicates their ability to accurately process culturally rich and diverse figurative language, such as proverbs. To address this, we introduce *Jawaher*, a benchmark designed to assess LLMs' capacity to comprehend and interpret Arabic proverbs. *Jawaher* includes proverbs from various Arabic dialects, along with idiomatic translations and explanations. Through extensive evaluations of both open- and closed-source models, we find that while LLMs can generate idiomatically accurate translations, they struggle with producing culturally nuanced and contextually relevant explanations. These findings highlight the need for ongoing model refinement and dataset expansion to bridge the cultural gap in figurative language processing."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="magdy-etal-2025-jawaher">
<titleInfo>
<title>JAWAHER: A Multidialectal Dataset of Arabic Proverbs for LLM Benchmarking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="given">Mohamed</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sang</namePart>
<namePart type="given">Yun</namePart>
<namePart type="family">Kwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fakhraddin</namePart>
<namePart type="family">Alwajih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Safaa</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Abdelfadil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shady</namePart>
<namePart type="family">Shehata</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>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Recent advancements in instruction fine-tuning, alignment methods such as reinforcement learning from human feedback (RLHF), and optimization techniques like direct preference optimization (DPO), have significantly enhanced the adaptability of large language models (LLMs) to user preferences. However, despite these innovations, many LLMs continue to exhibit biases toward Western, Anglo-centric, or American cultures, with performance on English data consistently surpassing that of other languages. This reveals a persistent cultural gap in LLMs, which complicates their ability to accurately process culturally rich and diverse figurative language, such as proverbs. To address this, we introduce *Jawaher*, a benchmark designed to assess LLMs’ capacity to comprehend and interpret Arabic proverbs. *Jawaher* includes proverbs from various Arabic dialects, along with idiomatic translations and explanations. Through extensive evaluations of both open- and closed-source models, we find that while LLMs can generate idiomatically accurate translations, they struggle with producing culturally nuanced and contextually relevant explanations. These findings highlight the need for ongoing model refinement and dataset expansion to bridge the cultural gap in figurative language processing.</abstract>
<identifier type="citekey">magdy-etal-2025-jawaher</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.613</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.613/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>12320</start>
<end>12341</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JAWAHER: A Multidialectal Dataset of Arabic Proverbs for LLM Benchmarking
%A Magdy, Samar Mohamed
%A Kwon, Sang Yun
%A Alwajih, Fakhraddin
%A Abdelfadil, Safaa Taher
%A Shehata, Shady
%A Abdul-Mageed, Muhammad
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F magdy-etal-2025-jawaher
%X Recent advancements in instruction fine-tuning, alignment methods such as reinforcement learning from human feedback (RLHF), and optimization techniques like direct preference optimization (DPO), have significantly enhanced the adaptability of large language models (LLMs) to user preferences. However, despite these innovations, many LLMs continue to exhibit biases toward Western, Anglo-centric, or American cultures, with performance on English data consistently surpassing that of other languages. This reveals a persistent cultural gap in LLMs, which complicates their ability to accurately process culturally rich and diverse figurative language, such as proverbs. To address this, we introduce *Jawaher*, a benchmark designed to assess LLMs’ capacity to comprehend and interpret Arabic proverbs. *Jawaher* includes proverbs from various Arabic dialects, along with idiomatic translations and explanations. Through extensive evaluations of both open- and closed-source models, we find that while LLMs can generate idiomatically accurate translations, they struggle with producing culturally nuanced and contextually relevant explanations. These findings highlight the need for ongoing model refinement and dataset expansion to bridge the cultural gap in figurative language processing.
%R 10.18653/v1/2025.naacl-long.613
%U https://aclanthology.org/2025.naacl-long.613/
%U https://doi.org/10.18653/v1/2025.naacl-long.613
%P 12320-12341
Markdown (Informal)
[JAWAHER: A Multidialectal Dataset of Arabic Proverbs for LLM Benchmarking](https://aclanthology.org/2025.naacl-long.613/) (Magdy et al., NAACL 2025)
ACL
- Samar Mohamed Magdy, Sang Yun Kwon, Fakhraddin Alwajih, Safaa Taher Abdelfadil, Shady Shehata, and Muhammad Abdul-Mageed. 2025. JAWAHER: A Multidialectal Dataset of Arabic Proverbs for LLM Benchmarking. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 12320–12341, Albuquerque, New Mexico. Association for Computational Linguistics.