@inproceedings{ashraf-etal-2026-reglat,
title = "{REGLAT} at {H}allu{S}coring-2026: A Multistage Approach for {A}rabic Hallucination Detection",
author = "Ashraf, Nsrin and
Abdellatif, Mariam M. and
Francies, Mariam and
Fetouh, Ahmed M. and
Nayel, Hamada",
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.142/",
pages = "1146--1153",
ISBN = "979-8-89176-497-2",
abstract = "This paper presents a multistage ensemble-based approach developed for the HalluScoring-2026 shared task on Arabic hallucination detection. The proposed system combines three Arabic pretrained language encoders: MARBERTv2, CAMeLBERT, and ARBERT. The diverse linguistic representations captured by these models enable the ensemble to improve the robustness and discriminative capability of hallucination detection compared to the individual encoders. On the development set, the ensemble achieved an AUC-ROC of 0.9413, Macro-F1 of 0.8704, and an AUC-PR of 0.9610, outperforming the individual models. On the official test set, the system achieved an AUC-ROC of 0.7717, Macro-F1 of 0.6576, and an AUC-PR of 0.9181. These results secured the highest overall ranking among all submitted systems, placing our system first in the HalluScoring-2026 shared task. Further analysis reveals substantial variation in detection performance across generator models and linguistic phenomena, with subtle factual deviations, dialectal and culturally specific expressions, and unusually long responses posing particular challenges. Overall, the findings demonstrate the effectiveness of combining distinct Arabic-specific pretrained encoders for robust Arabic hallucination detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ashraf-etal-2026-reglat">
<titleInfo>
<title>REGLAT at HalluScoring-2026: A Multistage Approach for Arabic Hallucination Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nsrin</namePart>
<namePart type="family">Ashraf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariam</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Abdellatif</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariam</namePart>
<namePart type="family">Francies</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Fetouh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamada</namePart>
<namePart type="family">Nayel</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>This paper presents a multistage ensemble-based approach developed for the HalluScoring-2026 shared task on Arabic hallucination detection. The proposed system combines three Arabic pretrained language encoders: MARBERTv2, CAMeLBERT, and ARBERT. The diverse linguistic representations captured by these models enable the ensemble to improve the robustness and discriminative capability of hallucination detection compared to the individual encoders. On the development set, the ensemble achieved an AUC-ROC of 0.9413, Macro-F1 of 0.8704, and an AUC-PR of 0.9610, outperforming the individual models. On the official test set, the system achieved an AUC-ROC of 0.7717, Macro-F1 of 0.6576, and an AUC-PR of 0.9181. These results secured the highest overall ranking among all submitted systems, placing our system first in the HalluScoring-2026 shared task. Further analysis reveals substantial variation in detection performance across generator models and linguistic phenomena, with subtle factual deviations, dialectal and culturally specific expressions, and unusually long responses posing particular challenges. Overall, the findings demonstrate the effectiveness of combining distinct Arabic-specific pretrained encoders for robust Arabic hallucination detection.</abstract>
<identifier type="citekey">ashraf-etal-2026-reglat</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.142/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1146</start>
<end>1153</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T REGLAT at HalluScoring-2026: A Multistage Approach for Arabic Hallucination Detection
%A Ashraf, Nsrin
%A Abdellatif, Mariam M.
%A Francies, Mariam
%A Fetouh, Ahmed M.
%A Nayel, Hamada
%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 ashraf-etal-2026-reglat
%X This paper presents a multistage ensemble-based approach developed for the HalluScoring-2026 shared task on Arabic hallucination detection. The proposed system combines three Arabic pretrained language encoders: MARBERTv2, CAMeLBERT, and ARBERT. The diverse linguistic representations captured by these models enable the ensemble to improve the robustness and discriminative capability of hallucination detection compared to the individual encoders. On the development set, the ensemble achieved an AUC-ROC of 0.9413, Macro-F1 of 0.8704, and an AUC-PR of 0.9610, outperforming the individual models. On the official test set, the system achieved an AUC-ROC of 0.7717, Macro-F1 of 0.6576, and an AUC-PR of 0.9181. These results secured the highest overall ranking among all submitted systems, placing our system first in the HalluScoring-2026 shared task. Further analysis reveals substantial variation in detection performance across generator models and linguistic phenomena, with subtle factual deviations, dialectal and culturally specific expressions, and unusually long responses posing particular challenges. Overall, the findings demonstrate the effectiveness of combining distinct Arabic-specific pretrained encoders for robust Arabic hallucination detection.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.142/
%P 1146-1153
Markdown (Informal)
[REGLAT at HalluScoring-2026: A Multistage Approach for Arabic Hallucination Detection](https://aclanthology.org/2026.arabicnlp-sharedtasks.142/) (Ashraf et al., ArabicNLP 2026)
ACL