@inproceedings{younis-2026-ahmed-younis,
title = "Ahmed Younis at {I}mage{E}val 2026 Shared Tasks: The Judge Needs a Prior and the Task Needs a Constraint",
author = "Younis, Ahmed",
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.94/",
pages = "753--758",
ISBN = "979-8-89176-497-2",
abstract = "Across two ImageEval 2026 tracks, our best results came from analyzing the evaluation machinery rather than from a stronger model, yielding 1st place on hallucination detection (Task 1b, Modern Standard Arabic) and 4th on CRAI-Bench (Task 2). On CRAI-Bench, which asks systems to predict human cultural-accuracy scores for AI-generated images of Qatari scenes, a blind frequency prior that never looks at an image reaches dev Spearman 0.6878, above the organizers' GPT-4-as-judge baseline of 0.625; adding two vision judges, with blend weights tuned against the global ranking metric rather than by scene-level cross-validation, reaches 0.7806 on the blind test. The weighting correction alone is worth +0.0296 test Spearman, because scene-level cross-validation is structurally blind to the within-cell ranking that judges contribute. On Task 1b, reframing ``label three statements true/false'' as ``select the one grounded statement'' makes invalid labelings structurally impossible and reaches 0.964 combined accuracy on the blind test, against an official baseline of 0.508. A matched-model ablation shows most of that headline gap is the underlying judge, but the constraint still adds +0.026 combined accuracy and eliminates the 4.0{\%} of items that otherwise receive structurally invalid labelings; meanwhile upgrading to a stronger judge is worth nothing measurable and a three-model vote scored lower."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="younis-2026-ahmed-younis">
<titleInfo>
<title>Ahmed Younis at ImageEval 2026 Shared Tasks: The Judge Needs a Prior and the Task Needs a Constraint</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Younis</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>Across two ImageEval 2026 tracks, our best results came from analyzing the evaluation machinery rather than from a stronger model, yielding 1st place on hallucination detection (Task 1b, Modern Standard Arabic) and 4th on CRAI-Bench (Task 2). On CRAI-Bench, which asks systems to predict human cultural-accuracy scores for AI-generated images of Qatari scenes, a blind frequency prior that never looks at an image reaches dev Spearman 0.6878, above the organizers’ GPT-4-as-judge baseline of 0.625; adding two vision judges, with blend weights tuned against the global ranking metric rather than by scene-level cross-validation, reaches 0.7806 on the blind test. The weighting correction alone is worth +0.0296 test Spearman, because scene-level cross-validation is structurally blind to the within-cell ranking that judges contribute. On Task 1b, reframing “label three statements true/false” as “select the one grounded statement” makes invalid labelings structurally impossible and reaches 0.964 combined accuracy on the blind test, against an official baseline of 0.508. A matched-model ablation shows most of that headline gap is the underlying judge, but the constraint still adds +0.026 combined accuracy and eliminates the 4.0% of items that otherwise receive structurally invalid labelings; meanwhile upgrading to a stronger judge is worth nothing measurable and a three-model vote scored lower.</abstract>
<identifier type="citekey">younis-2026-ahmed-younis</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.94/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>753</start>
<end>758</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ahmed Younis at ImageEval 2026 Shared Tasks: The Judge Needs a Prior and the Task Needs a Constraint
%A Younis, Ahmed
%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 younis-2026-ahmed-younis
%X Across two ImageEval 2026 tracks, our best results came from analyzing the evaluation machinery rather than from a stronger model, yielding 1st place on hallucination detection (Task 1b, Modern Standard Arabic) and 4th on CRAI-Bench (Task 2). On CRAI-Bench, which asks systems to predict human cultural-accuracy scores for AI-generated images of Qatari scenes, a blind frequency prior that never looks at an image reaches dev Spearman 0.6878, above the organizers’ GPT-4-as-judge baseline of 0.625; adding two vision judges, with blend weights tuned against the global ranking metric rather than by scene-level cross-validation, reaches 0.7806 on the blind test. The weighting correction alone is worth +0.0296 test Spearman, because scene-level cross-validation is structurally blind to the within-cell ranking that judges contribute. On Task 1b, reframing “label three statements true/false” as “select the one grounded statement” makes invalid labelings structurally impossible and reaches 0.964 combined accuracy on the blind test, against an official baseline of 0.508. A matched-model ablation shows most of that headline gap is the underlying judge, but the constraint still adds +0.026 combined accuracy and eliminates the 4.0% of items that otherwise receive structurally invalid labelings; meanwhile upgrading to a stronger judge is worth nothing measurable and a three-model vote scored lower.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.94/
%P 753-758
Markdown (Informal)
[Ahmed Younis at ImageEval 2026 Shared Tasks: The Judge Needs a Prior and the Task Needs a Constraint](https://aclanthology.org/2026.arabicnlp-sharedtasks.94/) (Younis, ArabicNLP 2026)
ACL