@inproceedings{rashid-2026-ayahverse,
title = "{A}yah{V}erse at {H}allu{S}coring-2026: Category-Aware {A}rabic Hallucination Detection with Multi-Layer Representations",
author = "Rashid, Ibad-ur-Rehman",
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.140/",
pages = "1131--1137",
ISBN = "979-8-89176-497-2",
abstract = "We present our submission to HalluScoring 2026, an ArabicNLP shared task on hallucination detection and answer recovery in Arabic LLM outputs. For Track 1, our submitted baseline fine-tunes CAMeLBERT for binary hallucination detection, achieving 0.921 and 0.763 AUC-ROC on the development and test sets of Task 1.1, and 0.749 and 0.729 on Task 1.2, respectively. We further conduct post-submission ablations with intermediate-layer supervision and category embeddings to study their effect on generalization. The combined model achieves 0.929 AUC-ROC on Task 1.1 and 0.777 on Task 1.2 development sets. For Track 2, we separate hallucination detection from answer selection, using CAMeLBERT for detection and a decoder-based, QLoRA-tuned AceGPT-v2-8B-Chat for option selection. The system achieves combined scores of 0.784 on Task 2.1 and 0.829 on Task 2.2 on the validation sets, improving substantially over the corresponding zero-shot baselines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rashid-2026-ayahverse">
<titleInfo>
<title>AyahVerse at HalluScoring-2026: Category-Aware Arabic Hallucination Detection with Multi-Layer Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ibad-ur-Rehman</namePart>
<namePart type="family">Rashid</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 our submission to HalluScoring 2026, an ArabicNLP shared task on hallucination detection and answer recovery in Arabic LLM outputs. For Track 1, our submitted baseline fine-tunes CAMeLBERT for binary hallucination detection, achieving 0.921 and 0.763 AUC-ROC on the development and test sets of Task 1.1, and 0.749 and 0.729 on Task 1.2, respectively. We further conduct post-submission ablations with intermediate-layer supervision and category embeddings to study their effect on generalization. The combined model achieves 0.929 AUC-ROC on Task 1.1 and 0.777 on Task 1.2 development sets. For Track 2, we separate hallucination detection from answer selection, using CAMeLBERT for detection and a decoder-based, QLoRA-tuned AceGPT-v2-8B-Chat for option selection. The system achieves combined scores of 0.784 on Task 2.1 and 0.829 on Task 2.2 on the validation sets, improving substantially over the corresponding zero-shot baselines.</abstract>
<identifier type="citekey">rashid-2026-ayahverse</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.140/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1131</start>
<end>1137</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AyahVerse at HalluScoring-2026: Category-Aware Arabic Hallucination Detection with Multi-Layer Representations
%A Rashid, Ibad-ur-Rehman
%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 rashid-2026-ayahverse
%X We present our submission to HalluScoring 2026, an ArabicNLP shared task on hallucination detection and answer recovery in Arabic LLM outputs. For Track 1, our submitted baseline fine-tunes CAMeLBERT for binary hallucination detection, achieving 0.921 and 0.763 AUC-ROC on the development and test sets of Task 1.1, and 0.749 and 0.729 on Task 1.2, respectively. We further conduct post-submission ablations with intermediate-layer supervision and category embeddings to study their effect on generalization. The combined model achieves 0.929 AUC-ROC on Task 1.1 and 0.777 on Task 1.2 development sets. For Track 2, we separate hallucination detection from answer selection, using CAMeLBERT for detection and a decoder-based, QLoRA-tuned AceGPT-v2-8B-Chat for option selection. The system achieves combined scores of 0.784 on Task 2.1 and 0.829 on Task 2.2 on the validation sets, improving substantially over the corresponding zero-shot baselines.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.140/
%P 1131-1137
Markdown (Informal)
[AyahVerse at HalluScoring-2026: Category-Aware Arabic Hallucination Detection with Multi-Layer Representations](https://aclanthology.org/2026.arabicnlp-sharedtasks.140/) (Rashid, ArabicNLP 2026)
ACL