@inproceedings{al-wazrah-etal-2025-evaluation,
title = "Evaluation of Large Language Models on {A}rabic Punctuation Prediction",
author = "Al Wazrah, Asma Ali and
Altamimi, Afrah and
Aljasim, Hawra and
Alshammari, Waad and
Al-Matham, Rawan and
Elnashar, Omar and
Amin, Mohamed and
AlOsaimy, Abdulrahman",
editor = "El-Haj, Mo",
booktitle = "Proceedings of the 1st Workshop on NLP for Languages Using Arabic Script",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.abjadnlp-1.15/",
pages = "144--154",
abstract = "The linguistic inclusivity of Large Language Models (LLMs) such as ChatGPT, Gemni, JAIS, and AceGPT has not been sufficiently explored, particularly in their handling of low-resource languages like Arabic compared to English. While these models have shown impressive performance across various tasks, their effectiveness in Arabic remains under-examined. Punctuation, critical for sentence structure and comprehension in tasks like speech analysis, synthesis, and machine translation, requires precise prediction. This paper assesses seven LLMs: GPT4-o, Gemni1.5, JAIS, AceGPT, SILMA, ALLaM, and CommandR+ for Arabic punctuation prediction. Additionally, the performance of fine-tuned AraBERT is compared with these models in zero-shot and few-shot settings using a proposed Arabic punctuation prediction corpus of 10,044 sentences. The experiments demonstrate that while AraBERT performs well for specific punctuation marks, LLMs show significant promise in zero-shot learning, with further improvements in few-shot scenarios. These findings highlight the potential of LLMs to enhance the automation and accuracy of Arabic text processing."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-wazrah-etal-2025-evaluation">
<titleInfo>
<title>Evaluation of Large Language Models on Arabic Punctuation Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="given">Ali</namePart>
<namePart type="family">Al Wazrah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afrah</namePart>
<namePart type="family">Altamimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hawra</namePart>
<namePart type="family">Aljasim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Waad</namePart>
<namePart type="family">Alshammari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Al-Matham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="family">Elnashar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Amin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulrahman</namePart>
<namePart type="family">AlOsaimy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on NLP for Languages Using Arabic Script</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mo</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The linguistic inclusivity of Large Language Models (LLMs) such as ChatGPT, Gemni, JAIS, and AceGPT has not been sufficiently explored, particularly in their handling of low-resource languages like Arabic compared to English. While these models have shown impressive performance across various tasks, their effectiveness in Arabic remains under-examined. Punctuation, critical for sentence structure and comprehension in tasks like speech analysis, synthesis, and machine translation, requires precise prediction. This paper assesses seven LLMs: GPT4-o, Gemni1.5, JAIS, AceGPT, SILMA, ALLaM, and CommandR+ for Arabic punctuation prediction. Additionally, the performance of fine-tuned AraBERT is compared with these models in zero-shot and few-shot settings using a proposed Arabic punctuation prediction corpus of 10,044 sentences. The experiments demonstrate that while AraBERT performs well for specific punctuation marks, LLMs show significant promise in zero-shot learning, with further improvements in few-shot scenarios. These findings highlight the potential of LLMs to enhance the automation and accuracy of Arabic text processing.</abstract>
<identifier type="citekey">al-wazrah-etal-2025-evaluation</identifier>
<location>
<url>https://aclanthology.org/2025.abjadnlp-1.15/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>144</start>
<end>154</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluation of Large Language Models on Arabic Punctuation Prediction
%A Al Wazrah, Asma Ali
%A Altamimi, Afrah
%A Aljasim, Hawra
%A Alshammari, Waad
%A Al-Matham, Rawan
%A Elnashar, Omar
%A Amin, Mohamed
%A AlOsaimy, Abdulrahman
%Y El-Haj, Mo
%S Proceedings of the 1st Workshop on NLP for Languages Using Arabic Script
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F al-wazrah-etal-2025-evaluation
%X The linguistic inclusivity of Large Language Models (LLMs) such as ChatGPT, Gemni, JAIS, and AceGPT has not been sufficiently explored, particularly in their handling of low-resource languages like Arabic compared to English. While these models have shown impressive performance across various tasks, their effectiveness in Arabic remains under-examined. Punctuation, critical for sentence structure and comprehension in tasks like speech analysis, synthesis, and machine translation, requires precise prediction. This paper assesses seven LLMs: GPT4-o, Gemni1.5, JAIS, AceGPT, SILMA, ALLaM, and CommandR+ for Arabic punctuation prediction. Additionally, the performance of fine-tuned AraBERT is compared with these models in zero-shot and few-shot settings using a proposed Arabic punctuation prediction corpus of 10,044 sentences. The experiments demonstrate that while AraBERT performs well for specific punctuation marks, LLMs show significant promise in zero-shot learning, with further improvements in few-shot scenarios. These findings highlight the potential of LLMs to enhance the automation and accuracy of Arabic text processing.
%U https://aclanthology.org/2025.abjadnlp-1.15/
%P 144-154
Markdown (Informal)
[Evaluation of Large Language Models on Arabic Punctuation Prediction](https://aclanthology.org/2025.abjadnlp-1.15/) (Al Wazrah et al., AbjadNLP 2025)
ACL
- Asma Ali Al Wazrah, Afrah Altamimi, Hawra Aljasim, Waad Alshammari, Rawan Al-Matham, Omar Elnashar, Mohamed Amin, and Abdulrahman AlOsaimy. 2025. Evaluation of Large Language Models on Arabic Punctuation Prediction. In Proceedings of the 1st Workshop on NLP for Languages Using Arabic Script, pages 144–154, Abu Dhabi, UAE. Association for Computational Linguistics.