@inproceedings{alyafeai-etal-2024-cidar,
title = "{CIDAR}: Culturally Relevant Instruction Dataset For {A}rabic",
author = "Alyafeai, Zaid and
Almubarak, Khalid and
Ashraf, Ahmed and
Alnuhait, Deema and
Alshahrani, Saied and
Abdulrahman, Gubran and
Ahmed, Gamil and
Gawah, Qais and
Saleh, Zead and
Ghaleb, Mustafa and
Ali, Yousef and
Al-shaibani, Maged",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.764",
pages = "12878--12901",
abstract = "Instruction tuning has emerged as a prominent methodology for teaching Large Language Models (LLMs) to follow instructions. However, current instruction datasets predominantly cater to English or are derived from English-dominated LLMs, leading to inherent biases toward Western culture. This bias negatively impacts non-English languages such as Arabic and the unique culture of the Arab region. This paper addresses this limitation by introducing CIDAR, the first open Arabic instruction-tuning dataset culturally aligned by native Arabic speakers. CIDAR contains 10,000 instruction and output pairs that represent the Arab region. We discuss the cultural relevance of CIDAR via the analysis and comparison to a few models fine-tuned on other datasets. Our experiments indicate that models fine-tuned on CIDAR achieve better cultural alignment compared to those fine-tuned on 30x more data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alyafeai-etal-2024-cidar">
<titleInfo>
<title>CIDAR: Culturally Relevant Instruction Dataset For Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Almubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Ashraf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deema</namePart>
<namePart type="family">Alnuhait</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saied</namePart>
<namePart type="family">Alshahrani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gubran</namePart>
<namePart type="family">Abdulrahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gamil</namePart>
<namePart type="family">Ahmed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qais</namePart>
<namePart type="family">Gawah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zead</namePart>
<namePart type="family">Saleh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="family">Ghaleb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yousef</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maged</namePart>
<namePart type="family">Al-shaibani</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>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Instruction tuning has emerged as a prominent methodology for teaching Large Language Models (LLMs) to follow instructions. However, current instruction datasets predominantly cater to English or are derived from English-dominated LLMs, leading to inherent biases toward Western culture. This bias negatively impacts non-English languages such as Arabic and the unique culture of the Arab region. This paper addresses this limitation by introducing CIDAR, the first open Arabic instruction-tuning dataset culturally aligned by native Arabic speakers. CIDAR contains 10,000 instruction and output pairs that represent the Arab region. We discuss the cultural relevance of CIDAR via the analysis and comparison to a few models fine-tuned on other datasets. Our experiments indicate that models fine-tuned on CIDAR achieve better cultural alignment compared to those fine-tuned on 30x more data.</abstract>
<identifier type="citekey">alyafeai-etal-2024-cidar</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.764</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>12878</start>
<end>12901</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CIDAR: Culturally Relevant Instruction Dataset For Arabic
%A Alyafeai, Zaid
%A Almubarak, Khalid
%A Ashraf, Ahmed
%A Alnuhait, Deema
%A Alshahrani, Saied
%A Abdulrahman, Gubran
%A Ahmed, Gamil
%A Gawah, Qais
%A Saleh, Zead
%A Ghaleb, Mustafa
%A Ali, Yousef
%A Al-shaibani, Maged
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F alyafeai-etal-2024-cidar
%X Instruction tuning has emerged as a prominent methodology for teaching Large Language Models (LLMs) to follow instructions. However, current instruction datasets predominantly cater to English or are derived from English-dominated LLMs, leading to inherent biases toward Western culture. This bias negatively impacts non-English languages such as Arabic and the unique culture of the Arab region. This paper addresses this limitation by introducing CIDAR, the first open Arabic instruction-tuning dataset culturally aligned by native Arabic speakers. CIDAR contains 10,000 instruction and output pairs that represent the Arab region. We discuss the cultural relevance of CIDAR via the analysis and comparison to a few models fine-tuned on other datasets. Our experiments indicate that models fine-tuned on CIDAR achieve better cultural alignment compared to those fine-tuned on 30x more data.
%U https://aclanthology.org/2024.findings-acl.764
%P 12878-12901
Markdown (Informal)
[CIDAR: Culturally Relevant Instruction Dataset For Arabic](https://aclanthology.org/2024.findings-acl.764) (Alyafeai et al., Findings 2024)
ACL
- Zaid Alyafeai, Khalid Almubarak, Ahmed Ashraf, Deema Alnuhait, Saied Alshahrani, Gubran Abdulrahman, Gamil Ahmed, Qais Gawah, Zead Saleh, Mustafa Ghaleb, Yousef Ali, and Maged Al-shaibani. 2024. CIDAR: Culturally Relevant Instruction Dataset For Arabic. In Findings of the Association for Computational Linguistics ACL 2024, pages 12878–12901, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.