@inproceedings{korched-2026-sanadai,
title = "{S}anad{AI} at {I}slamic{E}val 2026: Detecting Hallucinations in {A}rabic Islamic Citations through Span Detection and Hybrid Verification",
author = "Korched, Abir",
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.131/",
pages = "1067--1074",
ISBN = "979-8-89176-497-2",
abstract = "We present SanadAI, a modular system for the IslamicEval 2026 shared task on fine-grained hallucination detection and correction in Arabic Islamic content. We participate in Subtasks 1 and 2, which address citation span detection and hallucination detection, respectively. For Subtask 1, we fine-tune AraModernBERT as a BIO sequence tagger to identify Quranic verses ayah, Hadith text matn, transmission chains isnad, and claimed sources. Controlled Quranic and Hadith augmentation, together with Shamela-based hard-negative selection, substantially improves citation span detection over training on competition data alone. For Subtask 2, we use source-specific verification pipelines: Quranic evidence is verified through Arabic normalization and approximate matching, while Hadith evidence is verified using BGE-M3 dense retrieval, FAISS candidate search, lexical reranking, and semantic and entity-level evidence. SanadAI achieves 97.35{\%} Macro-F1 on Subtask 1 and 86.66{\%} official macro-accuracy on Subtask 2 on the hidden test set. Quranic verification is strongest at 96.89{\%}, whereas isnad verification remains the most challenging at 77.42{\%}, reflecting the difficulty of verifying transmission chains when the system relies on narrator compatibility with a retrieved Hadith rather than explicitly modeling narrator order and chain continuity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="korched-2026-sanadai">
<titleInfo>
<title>SanadAI at IslamicEval 2026: Detecting Hallucinations in Arabic Islamic Citations through Span Detection and Hybrid Verification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abir</namePart>
<namePart type="family">Korched</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>We present SanadAI, a modular system for the IslamicEval 2026 shared task on fine-grained hallucination detection and correction in Arabic Islamic content. We participate in Subtasks 1 and 2, which address citation span detection and hallucination detection, respectively. For Subtask 1, we fine-tune AraModernBERT as a BIO sequence tagger to identify Quranic verses ayah, Hadith text matn, transmission chains isnad, and claimed sources. Controlled Quranic and Hadith augmentation, together with Shamela-based hard-negative selection, substantially improves citation span detection over training on competition data alone. For Subtask 2, we use source-specific verification pipelines: Quranic evidence is verified through Arabic normalization and approximate matching, while Hadith evidence is verified using BGE-M3 dense retrieval, FAISS candidate search, lexical reranking, and semantic and entity-level evidence. SanadAI achieves 97.35% Macro-F1 on Subtask 1 and 86.66% official macro-accuracy on Subtask 2 on the hidden test set. Quranic verification is strongest at 96.89%, whereas isnad verification remains the most challenging at 77.42%, reflecting the difficulty of verifying transmission chains when the system relies on narrator compatibility with a retrieved Hadith rather than explicitly modeling narrator order and chain continuity.</abstract>
<identifier type="citekey">korched-2026-sanadai</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.131/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1067</start>
<end>1074</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SanadAI at IslamicEval 2026: Detecting Hallucinations in Arabic Islamic Citations through Span Detection and Hybrid Verification
%A Korched, Abir
%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 korched-2026-sanadai
%X We present SanadAI, a modular system for the IslamicEval 2026 shared task on fine-grained hallucination detection and correction in Arabic Islamic content. We participate in Subtasks 1 and 2, which address citation span detection and hallucination detection, respectively. For Subtask 1, we fine-tune AraModernBERT as a BIO sequence tagger to identify Quranic verses ayah, Hadith text matn, transmission chains isnad, and claimed sources. Controlled Quranic and Hadith augmentation, together with Shamela-based hard-negative selection, substantially improves citation span detection over training on competition data alone. For Subtask 2, we use source-specific verification pipelines: Quranic evidence is verified through Arabic normalization and approximate matching, while Hadith evidence is verified using BGE-M3 dense retrieval, FAISS candidate search, lexical reranking, and semantic and entity-level evidence. SanadAI achieves 97.35% Macro-F1 on Subtask 1 and 86.66% official macro-accuracy on Subtask 2 on the hidden test set. Quranic verification is strongest at 96.89%, whereas isnad verification remains the most challenging at 77.42%, reflecting the difficulty of verifying transmission chains when the system relies on narrator compatibility with a retrieved Hadith rather than explicitly modeling narrator order and chain continuity.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.131/
%P 1067-1074
Markdown (Informal)
[SanadAI at IslamicEval 2026: Detecting Hallucinations in Arabic Islamic Citations through Span Detection and Hybrid Verification](https://aclanthology.org/2026.arabicnlp-sharedtasks.131/) (Korched, ArabicNLP 2026)
ACL