@inproceedings{ghonem-2026-bayan,
title = "{B}ayan{\_}{CU} at {I}slamic{E}val 2026: Fine-Grained Hallucination Span Detection in {A}rabic {Q}uranic and {H}adith Texts",
author = "Ghonem, Samah",
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.133/",
pages = "1081--1087",
ISBN = "979-8-89176-497-2",
abstract = "Mitigating factual hallucinations in Large Language Model (LLM) responses is critical, especially when handling sacred Islamic text. This paper presents our system for the IslamicEval 2026 Shared Task-Subtask 1 (Span Detection), which requires extracting exact character-level spans and fragment labeling of religious citations in Arabic LLM-generated responses. We frame this as a supervised token-classification task, fine-tuning a monolingual bidirectional encoder (AraBERTv2). To process long sequences, we implement a sliding window chunking mechanism with an overlapping stride. We reconstruct final character boundaries using a post-processing heuristic that resolves overlapping token predictions. Furthermore, we apply a cascading false-positive filter using cross-type conflict resolution and category-specific minimum length thresholds. Our pipeline yields highly competitive results, achieving a Macro-F1 score of 0.9652 on the development set and a peak evaluation score of 0.9736 on the official-task test set."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghonem-2026-bayan">
<titleInfo>
<title>Bayan_CU at IslamicEval 2026: Fine-Grained Hallucination Span Detection in Arabic Quranic and Hadith Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samah</namePart>
<namePart type="family">Ghonem</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>Mitigating factual hallucinations in Large Language Model (LLM) responses is critical, especially when handling sacred Islamic text. This paper presents our system for the IslamicEval 2026 Shared Task-Subtask 1 (Span Detection), which requires extracting exact character-level spans and fragment labeling of religious citations in Arabic LLM-generated responses. We frame this as a supervised token-classification task, fine-tuning a monolingual bidirectional encoder (AraBERTv2). To process long sequences, we implement a sliding window chunking mechanism with an overlapping stride. We reconstruct final character boundaries using a post-processing heuristic that resolves overlapping token predictions. Furthermore, we apply a cascading false-positive filter using cross-type conflict resolution and category-specific minimum length thresholds. Our pipeline yields highly competitive results, achieving a Macro-F1 score of 0.9652 on the development set and a peak evaluation score of 0.9736 on the official-task test set.</abstract>
<identifier type="citekey">ghonem-2026-bayan</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.133/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1081</start>
<end>1087</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bayan_CU at IslamicEval 2026: Fine-Grained Hallucination Span Detection in Arabic Quranic and Hadith Texts
%A Ghonem, Samah
%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 ghonem-2026-bayan
%X Mitigating factual hallucinations in Large Language Model (LLM) responses is critical, especially when handling sacred Islamic text. This paper presents our system for the IslamicEval 2026 Shared Task-Subtask 1 (Span Detection), which requires extracting exact character-level spans and fragment labeling of religious citations in Arabic LLM-generated responses. We frame this as a supervised token-classification task, fine-tuning a monolingual bidirectional encoder (AraBERTv2). To process long sequences, we implement a sliding window chunking mechanism with an overlapping stride. We reconstruct final character boundaries using a post-processing heuristic that resolves overlapping token predictions. Furthermore, we apply a cascading false-positive filter using cross-type conflict resolution and category-specific minimum length thresholds. Our pipeline yields highly competitive results, achieving a Macro-F1 score of 0.9652 on the development set and a peak evaluation score of 0.9736 on the official-task test set.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.133/
%P 1081-1087
Markdown (Informal)
[Bayan_CU at IslamicEval 2026: Fine-Grained Hallucination Span Detection in Arabic Quranic and Hadith Texts](https://aclanthology.org/2026.arabicnlp-sharedtasks.133/) (Ghonem, ArabicNLP 2026)
ACL