@inproceedings{alkulaib-jlidi-2026-datalabku,
title = "{DATAL}ab{KU} at {I}mage{E}val 2026 Shared Tasks: Metric-Aware Cultural Evaluation for {CRAI}-Bench",
author = "AlKulaib, Lulwah and
Jlidi, 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.95/",
pages = "759--765",
ISBN = "979-8-89176-497-2",
abstract = "We present a reference-based evaluation framework for CRAI-Bench, Task 2 of ImageEval 2026. The method uses GPT-5.4 to extract cultural evidence from the reference image, caption, and generated image. This evidence is converted into metric-specific numerical features and mapped to CRAI scores using a small regressor trained on the released data. On the development set, the proposed approach improves composite Spearman correlation over direct GPT-5.4 scoring, with strong gains on certain metrics. We also analyze performance across caption versions and show that evaluation becomes less reliable for some dimensions as captions become more generic."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alkulaib-jlidi-2026-datalabku">
<titleInfo>
<title>DATALabKU at ImageEval 2026 Shared Tasks: Metric-Aware Cultural Evaluation for CRAI-Bench</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lulwah</namePart>
<namePart type="family">AlKulaib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Jlidi</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 a reference-based evaluation framework for CRAI-Bench, Task 2 of ImageEval 2026. The method uses GPT-5.4 to extract cultural evidence from the reference image, caption, and generated image. This evidence is converted into metric-specific numerical features and mapped to CRAI scores using a small regressor trained on the released data. On the development set, the proposed approach improves composite Spearman correlation over direct GPT-5.4 scoring, with strong gains on certain metrics. We also analyze performance across caption versions and show that evaluation becomes less reliable for some dimensions as captions become more generic.</abstract>
<identifier type="citekey">alkulaib-jlidi-2026-datalabku</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.95/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>759</start>
<end>765</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DATALabKU at ImageEval 2026 Shared Tasks: Metric-Aware Cultural Evaluation for CRAI-Bench
%A AlKulaib, Lulwah
%A Jlidi, 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 alkulaib-jlidi-2026-datalabku
%X We present a reference-based evaluation framework for CRAI-Bench, Task 2 of ImageEval 2026. The method uses GPT-5.4 to extract cultural evidence from the reference image, caption, and generated image. This evidence is converted into metric-specific numerical features and mapped to CRAI scores using a small regressor trained on the released data. On the development set, the proposed approach improves composite Spearman correlation over direct GPT-5.4 scoring, with strong gains on certain metrics. We also analyze performance across caption versions and show that evaluation becomes less reliable for some dimensions as captions become more generic.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.95/
%P 759-765
Markdown (Informal)
[DATALabKU at ImageEval 2026 Shared Tasks: Metric-Aware Cultural Evaluation for CRAI-Bench](https://aclanthology.org/2026.arabicnlp-sharedtasks.95/) (AlKulaib & Jlidi, ArabicNLP 2026)
ACL