@inproceedings{alwajih-etal-2024-peacock,
title = "Peacock: A Family of {A}rabic Multimodal Large Language Models and Benchmarks",
author = "Alwajih, Fakhraddin and
Nagoudi, El Moatez Billah and
Bhatia, Gagan and
Mohamed, Abdelrahman and
Abdul-Mageed, Muhammad",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.689",
pages = "12753--12776",
abstract = "Multimodal large language models (MLLMs) have proven effective in a wide range of tasks that require complex reasoning and linguistic comprehension. However, due to a lack of high-quality multimodal resources in languages other than English, the success of MLLMs remains relatively limited to English-based settings. This poses significant challenges in developing comparable models for other languages, even those with large speaker populations, such as Arabic. To alleviate this challenge, we introduce a comprehensive family of Arabic MLLMs, dubbed *Peacock*, with strong vision and language capabilities. Through comprehensive qualitative and quantitative analysis, we demonstrate the solid performance of our models on various visual reasoning tasks and further show their emerging dialectal potential. Additionally, we introduce *Henna*, a new benchmark specifically designed for assessing MLLMs on aspects related to Arabic culture, setting the first stone for culturally-aware Arabic MLLMs. The GitHub repository for the *Peacock* project is available at [https://github.com/UBC-NLP/peacock](https://github.com/UBC-NLP/peacock).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alwajih-etal-2024-peacock">
<titleInfo>
<title>Peacock: A Family of Arabic Multimodal Large Language Models and Benchmarks</title>
</titleInfo>
<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">El</namePart>
<namePart type="given">Moatez</namePart>
<namePart type="given">Billah</namePart>
<namePart type="family">Nagoudi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gagan</namePart>
<namePart type="family">Bhatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdelrahman</namePart>
<namePart type="family">Mohamed</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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal large language models (MLLMs) have proven effective in a wide range of tasks that require complex reasoning and linguistic comprehension. However, due to a lack of high-quality multimodal resources in languages other than English, the success of MLLMs remains relatively limited to English-based settings. This poses significant challenges in developing comparable models for other languages, even those with large speaker populations, such as Arabic. To alleviate this challenge, we introduce a comprehensive family of Arabic MLLMs, dubbed *Peacock*, with strong vision and language capabilities. Through comprehensive qualitative and quantitative analysis, we demonstrate the solid performance of our models on various visual reasoning tasks and further show their emerging dialectal potential. Additionally, we introduce *Henna*, a new benchmark specifically designed for assessing MLLMs on aspects related to Arabic culture, setting the first stone for culturally-aware Arabic MLLMs. The GitHub repository for the *Peacock* project is available at [https://github.com/UBC-NLP/peacock](https://github.com/UBC-NLP/peacock).</abstract>
<identifier type="citekey">alwajih-etal-2024-peacock</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.689</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>12753</start>
<end>12776</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Peacock: A Family of Arabic Multimodal Large Language Models and Benchmarks
%A Alwajih, Fakhraddin
%A Nagoudi, El Moatez Billah
%A Bhatia, Gagan
%A Mohamed, Abdelrahman
%A Abdul-Mageed, Muhammad
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F alwajih-etal-2024-peacock
%X Multimodal large language models (MLLMs) have proven effective in a wide range of tasks that require complex reasoning and linguistic comprehension. However, due to a lack of high-quality multimodal resources in languages other than English, the success of MLLMs remains relatively limited to English-based settings. This poses significant challenges in developing comparable models for other languages, even those with large speaker populations, such as Arabic. To alleviate this challenge, we introduce a comprehensive family of Arabic MLLMs, dubbed *Peacock*, with strong vision and language capabilities. Through comprehensive qualitative and quantitative analysis, we demonstrate the solid performance of our models on various visual reasoning tasks and further show their emerging dialectal potential. Additionally, we introduce *Henna*, a new benchmark specifically designed for assessing MLLMs on aspects related to Arabic culture, setting the first stone for culturally-aware Arabic MLLMs. The GitHub repository for the *Peacock* project is available at [https://github.com/UBC-NLP/peacock](https://github.com/UBC-NLP/peacock).
%U https://aclanthology.org/2024.acl-long.689
%P 12753-12776
Markdown (Informal)
[Peacock: A Family of Arabic Multimodal Large Language Models and Benchmarks](https://aclanthology.org/2024.acl-long.689) (Alwajih et al., ACL 2024)
ACL
- Fakhraddin Alwajih, El Moatez Billah Nagoudi, Gagan Bhatia, Abdelrahman Mohamed, and Muhammad Abdul-Mageed. 2024. Peacock: A Family of Arabic Multimodal Large Language Models and Benchmarks. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12753–12776, Bangkok, Thailand. Association for Computational Linguistics.