@inproceedings{mohamed-2026-ahmed,
title = "Ahmed Ayman at {I}mage{E}val 2026 Shared Tasks: Measurement-First Systems for Spoken {VQA} and Cultural Accuracy Evaluation",
author = "Mohamed, Ahmed Ayman Ahmed Ezzat",
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.89/",
pages = "711--720",
ISBN = "979-8-89176-497-2",
abstract = "We describe our systems for both ImageEval 2026 shared tasks. On Subtask 1a (spoken visual QA) we reach 0.962 on English and 0.834 on Modern Standard Arabic against baselines of 0.664 and 0.398, ranking first on the English track and second on MSA, while on Task 2 (CRAI-Bench) our judge ensemble reaches a test Spearman of 0.673 against 0.533 for our reproduction of the organizer baseline. Three effects account for most of these margins: answer-token bias (digit labels suppress the answer 0, and ordinal words are worth 0.35 accuracy), Arabic speech recognition (isolated from visual reasoning by the parallel track design), and tie-breaking (calibration collapses ranks and a second judge separates them, while error correlation of 0.89 rules out cancellation). A post-submission study on degraded audio finds four transcript-level interventions null and measures a 9{\%} answer-flip rate between identical runs at temperature 0, a noise floor for single-run ablations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohamed-2026-ahmed">
<titleInfo>
<title>Ahmed Ayman at ImageEval 2026 Shared Tasks: Measurement-First Systems for Spoken VQA and Cultural Accuracy Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="given">Ayman</namePart>
<namePart type="given">Ahmed</namePart>
<namePart type="given">Ezzat</namePart>
<namePart type="family">Mohamed</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 our systems for both ImageEval 2026 shared tasks. On Subtask 1a (spoken visual QA) we reach 0.962 on English and 0.834 on Modern Standard Arabic against baselines of 0.664 and 0.398, ranking first on the English track and second on MSA, while on Task 2 (CRAI-Bench) our judge ensemble reaches a test Spearman of 0.673 against 0.533 for our reproduction of the organizer baseline. Three effects account for most of these margins: answer-token bias (digit labels suppress the answer 0, and ordinal words are worth 0.35 accuracy), Arabic speech recognition (isolated from visual reasoning by the parallel track design), and tie-breaking (calibration collapses ranks and a second judge separates them, while error correlation of 0.89 rules out cancellation). A post-submission study on degraded audio finds four transcript-level interventions null and measures a 9% answer-flip rate between identical runs at temperature 0, a noise floor for single-run ablations.</abstract>
<identifier type="citekey">mohamed-2026-ahmed</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.89/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>711</start>
<end>720</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings %T Ahmed Ayman at ImageEval 2026 Shared Tasks: Measurement-First Systems for Spoken VQA and Cultural Accuracy Evaluation %A Mohamed, Ahmed Ayman Ahmed Ezzat %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 mohamed-2026-ahmed %X We describe our systems for both ImageEval 2026 shared tasks. On Subtask 1a (spoken visual QA) we reach 0.962 on English and 0.834 on Modern Standard Arabic against baselines of 0.664 and 0.398, ranking first on the English track and second on MSA, while on Task 2 (CRAI-Bench) our judge ensemble reaches a test Spearman of 0.673 against 0.533 for our reproduction of the organizer baseline. Three effects account for most of these margins: answer-token bias (digit labels suppress the answer 0, and ordinal words are worth 0.35 accuracy), Arabic speech recognition (isolated from visual reasoning by the parallel track design), and tie-breaking (calibration collapses ranks and a second judge separates them, while error correlation of 0.89 rules out cancellation). A post-submission study on degraded audio finds four transcript-level interventions null and measures a 9% answer-flip rate between identical runs at temperature 0, a noise floor for single-run ablations. %U https://aclanthology.org/2026.arabicnlp-sharedtasks.89/ %P 711-720
Markdown (Informal)
[Ahmed Ayman at ImageEval 2026 Shared Tasks: Measurement-First Systems for Spoken VQA and Cultural Accuracy Evaluation](https://aclanthology.org/2026.arabicnlp-sharedtasks.89/) (Mohamed, ArabicNLP 2026)