@inproceedings{mubarak-etal-2025-islamiceval,
title = "{I}slamic{E}val 2025: The First Shared Task of Capturing {LLM}s Hallucination in Islamic Content",
author = "Mubarak, Hamdy and
Malhas, Rana and
Mansour, Watheq and
Mohamed, Abubakr and
Fawzi, Mahmoud and
Hawasly, Majd and
Elsayed, Tamer and
Darwish, Kareem Mohamed and
Magdy, Walid",
editor = "Darwish, Kareem and
Ali, Ahmed and
Abu Farha, Ibrahim and
Touileb, Samia and
Zitouni, Imed and
Abdelali, Ahmed and
Al-Ghamdi, Sharefah and
Alkhereyf, Sakhar and
Zaghouani, Wajdi and
Khalifa, Salam and
AlKhamissi, Badr and
Almatham, Rawan and
Hamed, Injy and
Alyafeai, Zaid and
Alowisheq, Areeb and
Inoue, Go and
Mrini, Khalil and
Alshammari, Waad",
booktitle = "Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.arabicnlp-sharedtasks.67/",
pages = "480--493",
ISBN = "979-8-89176-356-2",
abstract = "Hallucination in Large Language Models (LLMs) remains a significant challenge and continues to draw substantial research attention. The problem becomes especially critical when hallucinations arise in sensitive domains, such as religious discourse. To address this gap, we introduce IslamicEval 2025{---}the first shared task specifically focused on evaluating and detecting hallucinations in Islamic content. The task consists of two subtasks: (1) Hallucination Detection and Correction of quoted verses (Ayahs) from the Holy Quran and quoted Hadiths; and (2) Qur{'}an and Hadith Question Answering, which assesses retrieval models and LLMs by requiring answers to be retrieved from grounded, authoritative sources. Thirteen teams participated in the final phase of the shared task, employing a range of pipelines and frameworks. Their diverse approaches underscore both the complexity of the task and the importance of effectively managing hallucinations in Islamic discourse."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mubarak-etal-2025-islamiceval">
<titleInfo>
<title>IslamicEval 2025: The First Shared Task of Capturing LLMs Hallucination in Islamic Content</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hamdy</namePart>
<namePart type="family">Mubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rana</namePart>
<namePart type="family">Malhas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Watheq</namePart>
<namePart type="family">Mansour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abubakr</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">Fawzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Majd</namePart>
<namePart type="family">Hawasly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="given">Mohamed</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Touileb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharefah</namePart>
<namePart type="family">Al-Ghamdi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Badr</namePart>
<namePart type="family">AlKhamissi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Areeb</namePart>
<namePart type="family">Alowisheq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Go</namePart>
<namePart type="family">Inoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Waad</namePart>
<namePart type="family">Alshammari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-356-2</identifier>
</relatedItem>
<abstract>Hallucination in Large Language Models (LLMs) remains a significant challenge and continues to draw substantial research attention. The problem becomes especially critical when hallucinations arise in sensitive domains, such as religious discourse. To address this gap, we introduce IslamicEval 2025—the first shared task specifically focused on evaluating and detecting hallucinations in Islamic content. The task consists of two subtasks: (1) Hallucination Detection and Correction of quoted verses (Ayahs) from the Holy Quran and quoted Hadiths; and (2) Qur’an and Hadith Question Answering, which assesses retrieval models and LLMs by requiring answers to be retrieved from grounded, authoritative sources. Thirteen teams participated in the final phase of the shared task, employing a range of pipelines and frameworks. Their diverse approaches underscore both the complexity of the task and the importance of effectively managing hallucinations in Islamic discourse.</abstract>
<identifier type="citekey">mubarak-etal-2025-islamiceval</identifier>
<location>
<url>https://aclanthology.org/2025.arabicnlp-sharedtasks.67/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>480</start>
<end>493</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IslamicEval 2025: The First Shared Task of Capturing LLMs Hallucination in Islamic Content
%A Mubarak, Hamdy
%A Malhas, Rana
%A Mansour, Watheq
%A Mohamed, Abubakr
%A Fawzi, Mahmoud
%A Hawasly, Majd
%A Elsayed, Tamer
%A Darwish, Kareem Mohamed
%A Magdy, Walid
%Y Darwish, Kareem
%Y Ali, Ahmed
%Y Abu Farha, Ibrahim
%Y Touileb, Samia
%Y Zitouni, Imed
%Y Abdelali, Ahmed
%Y Al-Ghamdi, Sharefah
%Y Alkhereyf, Sakhar
%Y Zaghouani, Wajdi
%Y Khalifa, Salam
%Y AlKhamissi, Badr
%Y Almatham, Rawan
%Y Hamed, Injy
%Y Alyafeai, Zaid
%Y Alowisheq, Areeb
%Y Inoue, Go
%Y Mrini, Khalil
%Y Alshammari, Waad
%S Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-356-2
%F mubarak-etal-2025-islamiceval
%X Hallucination in Large Language Models (LLMs) remains a significant challenge and continues to draw substantial research attention. The problem becomes especially critical when hallucinations arise in sensitive domains, such as religious discourse. To address this gap, we introduce IslamicEval 2025—the first shared task specifically focused on evaluating and detecting hallucinations in Islamic content. The task consists of two subtasks: (1) Hallucination Detection and Correction of quoted verses (Ayahs) from the Holy Quran and quoted Hadiths; and (2) Qur’an and Hadith Question Answering, which assesses retrieval models and LLMs by requiring answers to be retrieved from grounded, authoritative sources. Thirteen teams participated in the final phase of the shared task, employing a range of pipelines and frameworks. Their diverse approaches underscore both the complexity of the task and the importance of effectively managing hallucinations in Islamic discourse.
%U https://aclanthology.org/2025.arabicnlp-sharedtasks.67/
%P 480-493
Markdown (Informal)
[IslamicEval 2025: The First Shared Task of Capturing LLMs Hallucination in Islamic Content](https://aclanthology.org/2025.arabicnlp-sharedtasks.67/) (Mubarak et al., ArabicNLP 2025)
ACL
- Hamdy Mubarak, Rana Malhas, Watheq Mansour, Abubakr Mohamed, Mahmoud Fawzi, Majd Hawasly, Tamer Elsayed, Kareem Mohamed Darwish, and Walid Magdy. 2025. IslamicEval 2025: The First Shared Task of Capturing LLMs Hallucination in Islamic Content. In Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks, pages 480–493, Suzhou, China. Association for Computational Linguistics.