@inproceedings{sonbol-2026-hiast,
title = "{HIAST} at {I}slamic{E}val 2026: Context-Aware Hallucination Detection and Evidence-Guided Verification for {A}rabic Islamic Question Answering",
author = "Sonbol, Riad",
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.127/",
pages = "1040--1044",
ISBN = "979-8-89176-497-2",
abstract = "Large Language Models (LLMs) have significantly improved general-purpose question answering but remain prone to hallucinations in fact-sensitive domains such as religion. IslamicEval 2026 addresses these challenges by providing a fine-grained benchmark for evaluating hallucination and relevance in Arabic Islamic citations. This paper presents our approaches to three tasks: Citation Span Detection (Subtask 1), Hallucination Identification (Subtask 2), and Answer Relevance (Subtask 4). For Citation Span Detection, we formulate the problem as BIO-based token classification and fine-tune AraBERT using overlapping sliding-window encoding to process long responses effectively. For Hallucination Identification, we introduce a segment-level verification framework that augments each citation with adaptively extracted contextual evidence and citation-type information. For Answer Relevance, we combine hybrid lexical-semantic retrieval over authenticated Qur{'}anic and Hadith corpora with Transformer-based classification, enriching retrieved evidence with citation-specific context such as neighboring Ayat and explicit Surah{--}verse references. On the official test set, the proposed solutions achieved an F1 of 0.9725, an accuracy of 86.62{\%}, and a macro-F1 of 0.7721 for Subtasks 1, 2, and 4, respectively, demonstrating the effectiveness of the proposed approaches."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sonbol-2026-hiast">
<titleInfo>
<title>HIAST at IslamicEval 2026: Context-Aware Hallucination Detection and Evidence-Guided Verification for Arabic Islamic Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Riad</namePart>
<namePart type="family">Sonbol</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>Large Language Models (LLMs) have significantly improved general-purpose question answering but remain prone to hallucinations in fact-sensitive domains such as religion. IslamicEval 2026 addresses these challenges by providing a fine-grained benchmark for evaluating hallucination and relevance in Arabic Islamic citations. This paper presents our approaches to three tasks: Citation Span Detection (Subtask 1), Hallucination Identification (Subtask 2), and Answer Relevance (Subtask 4). For Citation Span Detection, we formulate the problem as BIO-based token classification and fine-tune AraBERT using overlapping sliding-window encoding to process long responses effectively. For Hallucination Identification, we introduce a segment-level verification framework that augments each citation with adaptively extracted contextual evidence and citation-type information. For Answer Relevance, we combine hybrid lexical-semantic retrieval over authenticated Qur’anic and Hadith corpora with Transformer-based classification, enriching retrieved evidence with citation-specific context such as neighboring Ayat and explicit Surah–verse references. On the official test set, the proposed solutions achieved an F1 of 0.9725, an accuracy of 86.62%, and a macro-F1 of 0.7721 for Subtasks 1, 2, and 4, respectively, demonstrating the effectiveness of the proposed approaches.</abstract>
<identifier type="citekey">sonbol-2026-hiast</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.127/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1040</start>
<end>1044</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HIAST at IslamicEval 2026: Context-Aware Hallucination Detection and Evidence-Guided Verification for Arabic Islamic Question Answering
%A Sonbol, Riad
%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 sonbol-2026-hiast
%X Large Language Models (LLMs) have significantly improved general-purpose question answering but remain prone to hallucinations in fact-sensitive domains such as religion. IslamicEval 2026 addresses these challenges by providing a fine-grained benchmark for evaluating hallucination and relevance in Arabic Islamic citations. This paper presents our approaches to three tasks: Citation Span Detection (Subtask 1), Hallucination Identification (Subtask 2), and Answer Relevance (Subtask 4). For Citation Span Detection, we formulate the problem as BIO-based token classification and fine-tune AraBERT using overlapping sliding-window encoding to process long responses effectively. For Hallucination Identification, we introduce a segment-level verification framework that augments each citation with adaptively extracted contextual evidence and citation-type information. For Answer Relevance, we combine hybrid lexical-semantic retrieval over authenticated Qur’anic and Hadith corpora with Transformer-based classification, enriching retrieved evidence with citation-specific context such as neighboring Ayat and explicit Surah–verse references. On the official test set, the proposed solutions achieved an F1 of 0.9725, an accuracy of 86.62%, and a macro-F1 of 0.7721 for Subtasks 1, 2, and 4, respectively, demonstrating the effectiveness of the proposed approaches.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.127/
%P 1040-1044
Markdown (Informal)
[HIAST at IslamicEval 2026: Context-Aware Hallucination Detection and Evidence-Guided Verification for Arabic Islamic Question Answering](https://aclanthology.org/2026.arabicnlp-sharedtasks.127/) (Sonbol, ArabicNLP 2026)
ACL