@inproceedings{zaky-etal-2026-taqwatech,
title = "Taqwatech at {I}slamic{E}val 2026: Contextual Span Detection and Corpus-Grounded Verification of Islamic Citations",
author = "Zaky, Sama Ayman and
Alsabagh, Basmala and
Reda, Kariim and
Mohsen, Abdelrahman",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference: Shared Tasks",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-sharedtasks.135/",
pages = "1093--1097",
ISBN = "979-8-89176-497-2",
abstract = "Reliable use of large language models in religious settings requires more than fluent text, since a generated answer may misquote Qur{'}anic verses or Hadiths, assign them to the wrong source, or provide an inaccurate narrator chain. This paper presents the Taqwatech systems for Subtasks{~}1 and{~}2 of IslamicEval 2026. For Subtask{~}1, we fine-tune CAMeLBERT-Mix as a BIO sequence-labeling model to detect Ayah, Hadith matn, isnad, and claimed-source spans. The predicted token labels are then converted into the character offsets required by the task. For Subtask{~}2, we develop a corpus-grounded verification system that combines Arabic normalization, lexical retrieval, character-level TF{--}IDF, Qur{'}anic verse matching, source validation, and narrator matching. On the official test set, our systems achieved a character-level macro-F1 score of 0.9683 for Subtask{~}1 and a macro accuracy of 0.9050 for Subtask{~}2. The results show strong performance in span detection and Qur{'}anic citation verification, while isnad verification remains the main area for improvement."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zaky-etal-2026-taqwatech">
<titleInfo>
<title>Taqwatech at IslamicEval 2026: Contextual Span Detection and Corpus-Grounded Verification of Islamic Citations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sama</namePart>
<namePart type="given">Ayman</namePart>
<namePart type="family">Zaky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Basmala</namePart>
<namePart type="family">Alsabagh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kariim</namePart>
<namePart type="family">Reda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdelrahman</namePart>
<namePart type="family">Mohsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</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">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</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">Samar</namePart>
<namePart type="family">Magdy</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">Injy</namePart>
<namePart type="family">Hamed</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">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-497-2</identifier>
</relatedItem>
<abstract>Reliable use of large language models in religious settings requires more than fluent text, since a generated answer may misquote Qur’anic verses or Hadiths, assign them to the wrong source, or provide an inaccurate narrator chain. This paper presents the Taqwatech systems for Subtasks 1 and 2 of IslamicEval 2026. For Subtask 1, we fine-tune CAMeLBERT-Mix as a BIO sequence-labeling model to detect Ayah, Hadith matn, isnad, and claimed-source spans. The predicted token labels are then converted into the character offsets required by the task. For Subtask 2, we develop a corpus-grounded verification system that combines Arabic normalization, lexical retrieval, character-level TF–IDF, Qur’anic verse matching, source validation, and narrator matching. On the official test set, our systems achieved a character-level macro-F1 score of 0.9683 for Subtask 1 and a macro accuracy of 0.9050 for Subtask 2. The results show strong performance in span detection and Qur’anic citation verification, while isnad verification remains the main area for improvement.</abstract>
<identifier type="citekey">zaky-etal-2026-taqwatech</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.135/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1093</start>
<end>1097</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Taqwatech at IslamicEval 2026: Contextual Span Detection and Corpus-Grounded Verification of Islamic Citations
%A Zaky, Sama Ayman
%A Alsabagh, Basmala
%A Reda, Kariim
%A Mohsen, Abdelrahman
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-497-2
%F zaky-etal-2026-taqwatech
%X Reliable use of large language models in religious settings requires more than fluent text, since a generated answer may misquote Qur’anic verses or Hadiths, assign them to the wrong source, or provide an inaccurate narrator chain. This paper presents the Taqwatech systems for Subtasks 1 and 2 of IslamicEval 2026. For Subtask 1, we fine-tune CAMeLBERT-Mix as a BIO sequence-labeling model to detect Ayah, Hadith matn, isnad, and claimed-source spans. The predicted token labels are then converted into the character offsets required by the task. For Subtask 2, we develop a corpus-grounded verification system that combines Arabic normalization, lexical retrieval, character-level TF–IDF, Qur’anic verse matching, source validation, and narrator matching. On the official test set, our systems achieved a character-level macro-F1 score of 0.9683 for Subtask 1 and a macro accuracy of 0.9050 for Subtask 2. The results show strong performance in span detection and Qur’anic citation verification, while isnad verification remains the main area for improvement.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.135/
%P 1093-1097
Markdown (Informal)
[Taqwatech at IslamicEval 2026: Contextual Span Detection and Corpus-Grounded Verification of Islamic Citations](https://aclanthology.org/2026.arabicnlp-sharedtasks.135/) (Zaky et al., ArabicNLP 2026)
ACL