@inproceedings{sheikh-2026-visioneval,
title = "{V}ision{E}val at {I}mage{E}val 2026 Shared Tasks: Forced-Choice Reformulation for Hallucination Detection and a Version-Prior Baseline for Cultural Relevance",
author = "Sheikh, Md. Faisal",
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.90/",
pages = "721--729",
ISBN = "979-8-89176-497-2",
abstract = "We describe the VisionEval submissions to ImageEval 2026, covering Task 1b in the English and MSA tracks and Task 2 (CRAI-Bench). For Task 1b the three statements of an item share a stem and exactly one is grounded, so we replace the three independent True/False calls of the released baseline with a single three-way forced choice, read from the logits of the candidate digit tokens. The output then satisfies the one-true constraint by construction, and contrastive instability falls from the baseline 0.2674 to 0.0670 in English and from 0.4277 to 0.1010 in MSA. The organisers' baseline is Qwen2.5-VL-3B prompted one statement at a time, and it identifies the grounded statement about as often as our 7B system does in English (0.9310 against 0.9330), so most of that gap is the output format rather than perception or scale. Task 2 is handled by a six-parameter model over the caption version, which placed first of five teams at Spearman 0.8258; an analysis of what that model reads shows the version field is recoverable from the released instance identifiers, so the result characterises the benchmark more than the system. We also show that the five reported Task 1b columns collapse to one degree of freedom for any system marking one statement true per item, an identity satisfied exactly by all fourteen rows of the final standings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sheikh-2026-visioneval">
<titleInfo>
<title>VisionEval at ImageEval 2026 Shared Tasks: Forced-Choice Reformulation for Hallucination Detection and a Version-Prior Baseline for Cultural Relevance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Faisal</namePart>
<namePart type="family">Sheikh</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 describe the VisionEval submissions to ImageEval 2026, covering Task 1b in the English and MSA tracks and Task 2 (CRAI-Bench). For Task 1b the three statements of an item share a stem and exactly one is grounded, so we replace the three independent True/False calls of the released baseline with a single three-way forced choice, read from the logits of the candidate digit tokens. The output then satisfies the one-true constraint by construction, and contrastive instability falls from the baseline 0.2674 to 0.0670 in English and from 0.4277 to 0.1010 in MSA. The organisers’ baseline is Qwen2.5-VL-3B prompted one statement at a time, and it identifies the grounded statement about as often as our 7B system does in English (0.9310 against 0.9330), so most of that gap is the output format rather than perception or scale. Task 2 is handled by a six-parameter model over the caption version, which placed first of five teams at Spearman 0.8258; an analysis of what that model reads shows the version field is recoverable from the released instance identifiers, so the result characterises the benchmark more than the system. We also show that the five reported Task 1b columns collapse to one degree of freedom for any system marking one statement true per item, an identity satisfied exactly by all fourteen rows of the final standings.</abstract>
<identifier type="citekey">sheikh-2026-visioneval</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.90/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>721</start>
<end>729</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VisionEval at ImageEval 2026 Shared Tasks: Forced-Choice Reformulation for Hallucination Detection and a Version-Prior Baseline for Cultural Relevance
%A Sheikh, Md. Faisal
%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 sheikh-2026-visioneval
%X We describe the VisionEval submissions to ImageEval 2026, covering Task 1b in the English and MSA tracks and Task 2 (CRAI-Bench). For Task 1b the three statements of an item share a stem and exactly one is grounded, so we replace the three independent True/False calls of the released baseline with a single three-way forced choice, read from the logits of the candidate digit tokens. The output then satisfies the one-true constraint by construction, and contrastive instability falls from the baseline 0.2674 to 0.0670 in English and from 0.4277 to 0.1010 in MSA. The organisers’ baseline is Qwen2.5-VL-3B prompted one statement at a time, and it identifies the grounded statement about as often as our 7B system does in English (0.9310 against 0.9330), so most of that gap is the output format rather than perception or scale. Task 2 is handled by a six-parameter model over the caption version, which placed first of five teams at Spearman 0.8258; an analysis of what that model reads shows the version field is recoverable from the released instance identifiers, so the result characterises the benchmark more than the system. We also show that the five reported Task 1b columns collapse to one degree of freedom for any system marking one statement true per item, an identity satisfied exactly by all fourteen rows of the final standings.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.90/
%P 721-729
Markdown (Informal)
[VisionEval at ImageEval 2026 Shared Tasks: Forced-Choice Reformulation for Hallucination Detection and a Version-Prior Baseline for Cultural Relevance](https://aclanthology.org/2026.arabicnlp-sharedtasks.90/) (Sheikh, ArabicNLP 2026)
ACL