@inproceedings{al-ani-hassaan-2026-detectorai,
title = "{D}etector{AI} at {A}r{G}uard Shared Tasks: Calibrated Multimodal and Label-Frequency-Aware Systems for {A}rabic Meme Safety Detection",
author = "Al-Ani, Mohammed and
Hassaan, Abdelrahman Sameh Ibrahim Ibrahim",
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.63/",
pages = "484--489",
ISBN = "979-8-89176-497-2",
abstract = "We present our systems for ArGuard 2026 Track A, which aims to detect harmful content in Arabic memes. The track includes two tasks: a binary task for identifying hateful memes (A1) and a multi-label task for predicting specific categories (A2). For A1, our approach combines a fine-tuned Qwen3-VL sequence classification model, Arabic text encoders, and a Qwen text LoRA classifier. We then apply top-$k$ calibration and make targeted adjustments based on model disagreements. On the official test set, our system reached a macro-F1 score of 0.7896 and an accuracy of 0.8200. For A2, we found that using thresholds from the development data caused us to overpredict common labels and miss rare ones. Our best A2 submission uses an ensemble of six Arabic text models, with label-frequency-aware top-$k$ calibration and rare-label boosting. This approach achieved a macro-F1 of 0.3601 and a micro-F1 of 0.5150. Overall, we found that careful calibration of a few fine-tuned Arabic and multimodal classifiers contributed more to our results than using larger zero-shot vision-language models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-ani-hassaan-2026-detectorai">
<titleInfo>
<title>DetectorAI at ArGuard Shared Tasks: Calibrated Multimodal and Label-Frequency-Aware Systems for Arabic Meme Safety Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Al-Ani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdelrahman</namePart>
<namePart type="given">Sameh</namePart>
<namePart type="given">Ibrahim</namePart>
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Hassaan</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 our systems for ArGuard 2026 Track A, which aims to detect harmful content in Arabic memes. The track includes two tasks: a binary task for identifying hateful memes (A1) and a multi-label task for predicting specific categories (A2). For A1, our approach combines a fine-tuned Qwen3-VL sequence classification model, Arabic text encoders, and a Qwen text LoRA classifier. We then apply top-k calibration and make targeted adjustments based on model disagreements. On the official test set, our system reached a macro-F1 score of 0.7896 and an accuracy of 0.8200. For A2, we found that using thresholds from the development data caused us to overpredict common labels and miss rare ones. Our best A2 submission uses an ensemble of six Arabic text models, with label-frequency-aware top-k calibration and rare-label boosting. This approach achieved a macro-F1 of 0.3601 and a micro-F1 of 0.5150. Overall, we found that careful calibration of a few fine-tuned Arabic and multimodal classifiers contributed more to our results than using larger zero-shot vision-language models.</abstract>
<identifier type="citekey">al-ani-hassaan-2026-detectorai</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.63/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>484</start>
<end>489</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DetectorAI at ArGuard Shared Tasks: Calibrated Multimodal and Label-Frequency-Aware Systems for Arabic Meme Safety Detection
%A Al-Ani, Mohammed
%A Hassaan, Abdelrahman Sameh Ibrahim Ibrahim
%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 al-ani-hassaan-2026-detectorai
%X We present our systems for ArGuard 2026 Track A, which aims to detect harmful content in Arabic memes. The track includes two tasks: a binary task for identifying hateful memes (A1) and a multi-label task for predicting specific categories (A2). For A1, our approach combines a fine-tuned Qwen3-VL sequence classification model, Arabic text encoders, and a Qwen text LoRA classifier. We then apply top-k calibration and make targeted adjustments based on model disagreements. On the official test set, our system reached a macro-F1 score of 0.7896 and an accuracy of 0.8200. For A2, we found that using thresholds from the development data caused us to overpredict common labels and miss rare ones. Our best A2 submission uses an ensemble of six Arabic text models, with label-frequency-aware top-k calibration and rare-label boosting. This approach achieved a macro-F1 of 0.3601 and a micro-F1 of 0.5150. Overall, we found that careful calibration of a few fine-tuned Arabic and multimodal classifiers contributed more to our results than using larger zero-shot vision-language models.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.63/
%P 484-489
Markdown (Informal)
[DetectorAI at ArGuard Shared Tasks: Calibrated Multimodal and Label-Frequency-Aware Systems for Arabic Meme Safety Detection](https://aclanthology.org/2026.arabicnlp-sharedtasks.63/) (Al-Ani & Hassaan, ArabicNLP 2026)
ACL