@inproceedings{zaman-rishta-2026-nile-nexus,
title = "Nile Nexus at {I}mage{E}val 2026 Shared Tasks: Single-Choice Reformulation and Confidence-Calibrated Refinement for Culturally Grounded Hallucination Detection",
author = "Zaman, Sumaiya and
Rishta, Miftahul Jannat",
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.87/",
pages = "697--702",
ISBN = "979-8-89176-497-2",
abstract = "Visual hallucination detection in culturally grounded images has remained challenging due to fine-grained visual distinctions and knowledge-dependent statements. In the ImageEval2026 / ArabicNLP26 AynVQA Shared Task, we have participated in Task 1b by developing a system based on Qwen2.5-VL-7B Instruct with 4-bit quantization. We have reformulated hallucination detection as a single choice selection problem to enforce the exactly one-correct-statement constraint and have introduced confidence-based selective refinement using paraphrase ensemble voting. Our final system has achieved 0.942 accuracy, 0.058 CI, 0.000 CFHR,0.942 Q+accuracy and 0.971 Q{\ensuremath{-}}accuracy, ranking 6th in the English track. Error analysis has revealed that the remaining failures have mostly stemmed from fine-grained cultural and visual grounding challenges rather than prediction inconsistency."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zaman-rishta-2026-nile-nexus">
<titleInfo>
<title>Nile Nexus at ImageEval 2026 Shared Tasks: Single-Choice Reformulation and Confidence-Calibrated Refinement for Culturally Grounded Hallucination Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sumaiya</namePart>
<namePart type="family">Zaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miftahul</namePart>
<namePart type="given">Jannat</namePart>
<namePart type="family">Rishta</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>Visual hallucination detection in culturally grounded images has remained challenging due to fine-grained visual distinctions and knowledge-dependent statements. In the ImageEval2026 / ArabicNLP26 AynVQA Shared Task, we have participated in Task 1b by developing a system based on Qwen2.5-VL-7B Instruct with 4-bit quantization. We have reformulated hallucination detection as a single choice selection problem to enforce the exactly one-correct-statement constraint and have introduced confidence-based selective refinement using paraphrase ensemble voting. Our final system has achieved 0.942 accuracy, 0.058 CI, 0.000 CFHR,0.942 Q+accuracy and 0.971 Q\ensuremath-accuracy, ranking 6th in the English track. Error analysis has revealed that the remaining failures have mostly stemmed from fine-grained cultural and visual grounding challenges rather than prediction inconsistency.</abstract>
<identifier type="citekey">zaman-rishta-2026-nile-nexus</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.87/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>697</start>
<end>702</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Nile Nexus at ImageEval 2026 Shared Tasks: Single-Choice Reformulation and Confidence-Calibrated Refinement for Culturally Grounded Hallucination Detection
%A Zaman, Sumaiya
%A Rishta, Miftahul Jannat
%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 zaman-rishta-2026-nile-nexus
%X Visual hallucination detection in culturally grounded images has remained challenging due to fine-grained visual distinctions and knowledge-dependent statements. In the ImageEval2026 / ArabicNLP26 AynVQA Shared Task, we have participated in Task 1b by developing a system based on Qwen2.5-VL-7B Instruct with 4-bit quantization. We have reformulated hallucination detection as a single choice selection problem to enforce the exactly one-correct-statement constraint and have introduced confidence-based selective refinement using paraphrase ensemble voting. Our final system has achieved 0.942 accuracy, 0.058 CI, 0.000 CFHR,0.942 Q+accuracy and 0.971 Q\ensuremath-accuracy, ranking 6th in the English track. Error analysis has revealed that the remaining failures have mostly stemmed from fine-grained cultural and visual grounding challenges rather than prediction inconsistency.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.87/
%P 697-702
Markdown (Informal)
[Nile Nexus at ImageEval 2026 Shared Tasks: Single-Choice Reformulation and Confidence-Calibrated Refinement for Culturally Grounded Hallucination Detection](https://aclanthology.org/2026.arabicnlp-sharedtasks.87/) (Zaman & Rishta, ArabicNLP 2026)
ACL