@inproceedings{bounab-etal-2026-helsinkiteam,
title = "{H}elsinki{T}eam at {H}allu{S}coring-2026: Domain-Adaptive {A}rabic Hallucination Detection and Answer Selection with {ALL}a{M}",
author = "Bounab, Yazid and
Benlamoudi, Azeddine and
Swaileh, Wassim and
Siv{\'e}n, Mia",
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.145/",
pages = "1165--1170",
ISBN = "979-8-89176-497-2",
abstract = "The rapid advancement of large language models (LLMs) has enabled powerful AI applications, yet hallucinations remain a major challenge to their reliability. As part of Track 2 of the HalluScoring 2026 shared task at ArabicNLP 2026, we present a system for detecting hallucinated answers and selecting the correct answer from six closely related candidates. We adapt the Arabic{--}English ALLaM-7B-Instruct model using Low-Rank Adaptation (LoRA) with domain-specific supervision from Qur{'}anic text, Hadith, Islamic law and inheritance, Islamic history, and general knowledge. The system jointly performs hallucination detection and answer selection, achieving 88.9{\%} accuracy and 88.6{\%} macro-F1 for hallucination detection, and 91.1{\%} answer selection accuracy on the 800-instance development set. Error analysis identifies geography and structured-output parsing as the main remaining weaknesses."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bounab-etal-2026-helsinkiteam">
<titleInfo>
<title>HelsinkiTeam at HalluScoring-2026: Domain-Adaptive Arabic Hallucination Detection and Answer Selection with ALLaM</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yazid</namePart>
<namePart type="family">Bounab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Azeddine</namePart>
<namePart type="family">Benlamoudi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wassim</namePart>
<namePart type="family">Swaileh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mia</namePart>
<namePart type="family">Sivén</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>The rapid advancement of large language models (LLMs) has enabled powerful AI applications, yet hallucinations remain a major challenge to their reliability. As part of Track 2 of the HalluScoring 2026 shared task at ArabicNLP 2026, we present a system for detecting hallucinated answers and selecting the correct answer from six closely related candidates. We adapt the Arabic–English ALLaM-7B-Instruct model using Low-Rank Adaptation (LoRA) with domain-specific supervision from Qur’anic text, Hadith, Islamic law and inheritance, Islamic history, and general knowledge. The system jointly performs hallucination detection and answer selection, achieving 88.9% accuracy and 88.6% macro-F1 for hallucination detection, and 91.1% answer selection accuracy on the 800-instance development set. Error analysis identifies geography and structured-output parsing as the main remaining weaknesses.</abstract>
<identifier type="citekey">bounab-etal-2026-helsinkiteam</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.145/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1165</start>
<end>1170</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HelsinkiTeam at HalluScoring-2026: Domain-Adaptive Arabic Hallucination Detection and Answer Selection with ALLaM
%A Bounab, Yazid
%A Benlamoudi, Azeddine
%A Swaileh, Wassim
%A Sivén, Mia
%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 bounab-etal-2026-helsinkiteam
%X The rapid advancement of large language models (LLMs) has enabled powerful AI applications, yet hallucinations remain a major challenge to their reliability. As part of Track 2 of the HalluScoring 2026 shared task at ArabicNLP 2026, we present a system for detecting hallucinated answers and selecting the correct answer from six closely related candidates. We adapt the Arabic–English ALLaM-7B-Instruct model using Low-Rank Adaptation (LoRA) with domain-specific supervision from Qur’anic text, Hadith, Islamic law and inheritance, Islamic history, and general knowledge. The system jointly performs hallucination detection and answer selection, achieving 88.9% accuracy and 88.6% macro-F1 for hallucination detection, and 91.1% answer selection accuracy on the 800-instance development set. Error analysis identifies geography and structured-output parsing as the main remaining weaknesses.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.145/
%P 1165-1170
Markdown (Informal)
[HelsinkiTeam at HalluScoring-2026: Domain-Adaptive Arabic Hallucination Detection and Answer Selection with ALLaM](https://aclanthology.org/2026.arabicnlp-sharedtasks.145/) (Bounab et al., ArabicNLP 2026)
ACL