@inproceedings{albahly-etal-2026-namaa,
title = "{NAMAA} Community at {H}allu{S}coring 2026: Beyond Predictive Performance: Reliability and Generalization in {A}rabic Hallucination Detection",
author = "Albahly, Najd and
Barmandah, Hassan and
Elsayed, Karim and
Ali, Hewida and
Abdullah, Yousef Ammar and
Nacar, Omer",
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.141/",
pages = "1138--1145",
ISBN = "979-8-89176-497-2",
abstract = "Reliable Arabic hallucination detection requires not only strong ranking performance but also robustness to distribution shift, calibrated probabilities, and useful uncertainty for selective prediction. We present the NAMAA Community{'}s submission to HalluScoring 2026 Task {\textasciitilde}1.1 and a set of post-submission diagnostic experiments. The scored, template-compliant system is a CAMeLBERT cross-encoder over the question and generated answer; it achieves 0.7596 ROC-AUC on the hidden test set, ranking third among seven teams. We compare this template-defined input path with reference-aware answer-pair models that use the gold answer. A CAMeLBERT input-framing ablation raises the unseen-question ROC-AUC from 0.8713 to 0.9272, while similar gains appear across ARBERT and MARBERTv2. Reference-free distillation recovers only a small portion of this advantage, whereas LoRA-InfoNCE substantially improves direct cosine discrimination. On a separately trained CAMeLBERT reliability replicate, temperature scaling reduces expected calibration error from 0.0993 to 0.0562, and MC-Dropout variance reduces retained-set error from 14.08{\%} to 8.35{\%} when the 30{\%} most uncertain cases are deferred. These results motivate reporting distributional generalization, calibration, and selective risk alongside ROC-AUC. Code and checkpoints for the scored submission are publicly available. [{\ensuremath{<}}https://github.com/NAMAA-ORG/HalluScoring-Arabic-Hallucination-Detection{\ensuremath{>}}]"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="albahly-etal-2026-namaa">
<titleInfo>
<title>NAMAA Community at HalluScoring 2026: Beyond Predictive Performance: Reliability and Generalization in Arabic Hallucination Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Najd</namePart>
<namePart type="family">Albahly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Barmandah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karim</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hewida</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yousef</namePart>
<namePart type="given">Ammar</namePart>
<namePart type="family">Abdullah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Nacar</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>Reliable Arabic hallucination detection requires not only strong ranking performance but also robustness to distribution shift, calibrated probabilities, and useful uncertainty for selective prediction. We present the NAMAA Community’s submission to HalluScoring 2026 Task ~1.1 and a set of post-submission diagnostic experiments. The scored, template-compliant system is a CAMeLBERT cross-encoder over the question and generated answer; it achieves 0.7596 ROC-AUC on the hidden test set, ranking third among seven teams. We compare this template-defined input path with reference-aware answer-pair models that use the gold answer. A CAMeLBERT input-framing ablation raises the unseen-question ROC-AUC from 0.8713 to 0.9272, while similar gains appear across ARBERT and MARBERTv2. Reference-free distillation recovers only a small portion of this advantage, whereas LoRA-InfoNCE substantially improves direct cosine discrimination. On a separately trained CAMeLBERT reliability replicate, temperature scaling reduces expected calibration error from 0.0993 to 0.0562, and MC-Dropout variance reduces retained-set error from 14.08% to 8.35% when the 30% most uncertain cases are deferred. These results motivate reporting distributional generalization, calibration, and selective risk alongside ROC-AUC. Code and checkpoints for the scored submission are publicly available. [\ensuremath<https://github.com/NAMAA-ORG/HalluScoring-Arabic-Hallucination-Detection\ensuremath>]</abstract>
<identifier type="citekey">albahly-etal-2026-namaa</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.141/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1138</start>
<end>1145</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NAMAA Community at HalluScoring 2026: Beyond Predictive Performance: Reliability and Generalization in Arabic Hallucination Detection
%A Albahly, Najd
%A Barmandah, Hassan
%A Elsayed, Karim
%A Ali, Hewida
%A Abdullah, Yousef Ammar
%A Nacar, Omer
%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 albahly-etal-2026-namaa
%X Reliable Arabic hallucination detection requires not only strong ranking performance but also robustness to distribution shift, calibrated probabilities, and useful uncertainty for selective prediction. We present the NAMAA Community’s submission to HalluScoring 2026 Task ~1.1 and a set of post-submission diagnostic experiments. The scored, template-compliant system is a CAMeLBERT cross-encoder over the question and generated answer; it achieves 0.7596 ROC-AUC on the hidden test set, ranking third among seven teams. We compare this template-defined input path with reference-aware answer-pair models that use the gold answer. A CAMeLBERT input-framing ablation raises the unseen-question ROC-AUC from 0.8713 to 0.9272, while similar gains appear across ARBERT and MARBERTv2. Reference-free distillation recovers only a small portion of this advantage, whereas LoRA-InfoNCE substantially improves direct cosine discrimination. On a separately trained CAMeLBERT reliability replicate, temperature scaling reduces expected calibration error from 0.0993 to 0.0562, and MC-Dropout variance reduces retained-set error from 14.08% to 8.35% when the 30% most uncertain cases are deferred. These results motivate reporting distributional generalization, calibration, and selective risk alongside ROC-AUC. Code and checkpoints for the scored submission are publicly available. [\ensuremath<https://github.com/NAMAA-ORG/HalluScoring-Arabic-Hallucination-Detection\ensuremath>]
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.141/
%P 1138-1145
Markdown (Informal)
[NAMAA Community at HalluScoring 2026: Beyond Predictive Performance: Reliability and Generalization in Arabic Hallucination Detection](https://aclanthology.org/2026.arabicnlp-sharedtasks.141/) (Albahly et al., ArabicNLP 2026)
ACL