@inproceedings{nam-takahashi-2026-anhnamxtanh,
title = "Anhnamxtanh at {H}allu{S}coring-2026: Counterfactual Cross-Checking for Hallucination Detection and Answer Verification in Islamic Knowledge",
author = "Nam, Nguyen Tu and
Takahashi, Hiroki",
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.143/",
pages = "1154--1159",
ISBN = "979-8-89176-497-2",
abstract = "Hallucination detection in Arabic Islamic question answering is challenging because fluent answers may misstate a verse, narration, ruling, attribution, or historical fact. The task jointly requires detecting hallucination and recovering the factually correct option. We introduce C3R, a Counterfactual Cross-Check Recognition framework that models this relation with two role-conditioned predictions from one Arabic language model: a truth role selects the factual option, while a match role selects the candidate that best represents the generated response. Training uses targeted counterfactual responses, hard distractors, option-order permutations, and completion-likelihood supervision without a cross-view consistency loss. At inference, C3R scores valid structured completions, maps predictions from permuted presentations back to semantic option identities, and derives the hallucination label from argmax agreement between the two roles. The cross-check is applied only at inference. With a QLoRA-adapted ALLaM backbone, C3R ranks first on the official test leaderboard with a final score of 0.8824, comprising 0.8673 macro-F1 and 0.8975 option accuracy. These results demonstrate the effectiveness of structured cross-role agreement for knowledge-sensitive hallucination detection and answer verification."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nam-takahashi-2026-anhnamxtanh">
<titleInfo>
<title>Anhnamxtanh at HalluScoring-2026: Counterfactual Cross-Checking for Hallucination Detection and Answer Verification in Islamic Knowledge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nguyen</namePart>
<namePart type="given">Tu</namePart>
<namePart type="family">Nam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Takahashi</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>Hallucination detection in Arabic Islamic question answering is challenging because fluent answers may misstate a verse, narration, ruling, attribution, or historical fact. The task jointly requires detecting hallucination and recovering the factually correct option. We introduce C3R, a Counterfactual Cross-Check Recognition framework that models this relation with two role-conditioned predictions from one Arabic language model: a truth role selects the factual option, while a match role selects the candidate that best represents the generated response. Training uses targeted counterfactual responses, hard distractors, option-order permutations, and completion-likelihood supervision without a cross-view consistency loss. At inference, C3R scores valid structured completions, maps predictions from permuted presentations back to semantic option identities, and derives the hallucination label from argmax agreement between the two roles. The cross-check is applied only at inference. With a QLoRA-adapted ALLaM backbone, C3R ranks first on the official test leaderboard with a final score of 0.8824, comprising 0.8673 macro-F1 and 0.8975 option accuracy. These results demonstrate the effectiveness of structured cross-role agreement for knowledge-sensitive hallucination detection and answer verification.</abstract>
<identifier type="citekey">nam-takahashi-2026-anhnamxtanh</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.143/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1154</start>
<end>1159</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Anhnamxtanh at HalluScoring-2026: Counterfactual Cross-Checking for Hallucination Detection and Answer Verification in Islamic Knowledge
%A Nam, Nguyen Tu
%A Takahashi, Hiroki
%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 nam-takahashi-2026-anhnamxtanh
%X Hallucination detection in Arabic Islamic question answering is challenging because fluent answers may misstate a verse, narration, ruling, attribution, or historical fact. The task jointly requires detecting hallucination and recovering the factually correct option. We introduce C3R, a Counterfactual Cross-Check Recognition framework that models this relation with two role-conditioned predictions from one Arabic language model: a truth role selects the factual option, while a match role selects the candidate that best represents the generated response. Training uses targeted counterfactual responses, hard distractors, option-order permutations, and completion-likelihood supervision without a cross-view consistency loss. At inference, C3R scores valid structured completions, maps predictions from permuted presentations back to semantic option identities, and derives the hallucination label from argmax agreement between the two roles. The cross-check is applied only at inference. With a QLoRA-adapted ALLaM backbone, C3R ranks first on the official test leaderboard with a final score of 0.8824, comprising 0.8673 macro-F1 and 0.8975 option accuracy. These results demonstrate the effectiveness of structured cross-role agreement for knowledge-sensitive hallucination detection and answer verification.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.143/
%P 1154-1159
Markdown (Informal)
[Anhnamxtanh at HalluScoring-2026: Counterfactual Cross-Checking for Hallucination Detection and Answer Verification in Islamic Knowledge](https://aclanthology.org/2026.arabicnlp-sharedtasks.143/) (Nam & Takahashi, ArabicNLP 2026)
ACL