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.
- Anthology ID:
- 2026.arabicnlp-sharedtasks.89
- Volume:
- [Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks](https://aclanthology.org/volumes/2026.arabicnlp-sharedtasks/)
- Month:
- October
- Year:
- 2026
- Address:
- Budapest, Hungary
- Editors:
- Muhammad Abdul-Mageed ,Tamer Elsayed ,Houda Bouamor ,Samhaa El-Beltagy ,Hend Al-Khalifa ,Ahmed Abdelali ,AbdelRahim Elmadany ,Abdellah El Mekki ,Kareem Darwish ,Sakhar Alkhereyf ,Hamzah Luqman ,Salam Khalifa ,Samar Magdy ,Zaid Alyafeai ,Injy Hamed ,Wajdi Zaghouani ,Imed Zitouni
- Venue:
- [ArabicNLP](https://aclanthology.org/venues/arabicnlp/)
- SIG:
- [SIGARAB](https://aclanthology.org/sigs/sigarab/)
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 711–720
- Language:
- URL:
- [https://aclanthology.org/2026.arabicnlp-sharedtasks.89/](https://aclanthology.org/2026.arabicnlp-sharedtasks.89/)
- DOI:
- Cite (ACL):
- Ahmed Ayman Ahmed Ezzat Mohamed. 2026. Ahmed Ayman at ImageEval 2026 Shared Tasks: Measurement-First Systems for Spoken VQA and Cultural Accuracy Evaluation . InProceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks , pages 711–720, Budapest, Hungary. Association for Computational Linguistics.
- Cite (Informal):
- Ahmed Ayman at ImageEval 2026 Shared Tasks: Measurement-First Systems for Spoken VQA and Cultural Accuracy Evaluation (Mohamed, ArabicNLP 2026)
- PDF:
- [https://aclanthology.org/2026.arabicnlp-sharedtasks.89.pdf](https://aclanthology.org/2026.arabicnlp-sharedtasks.89.pdf)