@inproceedings{djamai-etal-2026-namaa-arguard,
title = "{NAMAA} at {A}r{G}uard Shared Tasks: Multimodal Fusion, Vision{--}Language Model Adaptation, and In-Context Prompting for {A}rabic Hateful Meme Detection",
author = "Djamai, Abdelbasset and
Al Jallad, Khloud and
Mohamed Emad Elden, Fatimah and
Nacar, Omer",
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.62/",
pages = "470--483",
ISBN = "979-8-89176-497-2",
abstract = "Multimodal hate speech detection requires interpreting how an image and its accompanying text jointly construct a target, stance, or derogatory implication. In Arabic memes, this relation is often shaped by locally recognizable public figures, political references, visual analogies, and indirect humor, making either modality insufficient on its own. We tackle this problem in Track A of ArGuard 2026, covering binary hateful meme detection (A1) and fine-grained multi-label classification (A2). Our experiments compare jointly trained dual encoders, parameter-efficient vision{--}language model (VLM) adaptation, and training-free prompting. We fine-tune Qwen3-VL, Llama 3.2 Vision, and Gemma 4 with QLoRA using task-specific binary and multi-label objectives. We also build CLIP{--}MARBERTv2 and SigLIP{--}AraBERT-Twitter cross-attention systems and evaluate frozen VLMs with zero-shot prompting and in-context learning. Qwen3-VL achieves our highest A1 score (0.7610), while SigLIP{--}AraBERT-Twitter leads A2 (0.3851), where label sparsity and multi-label prediction remain challenging."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="djamai-etal-2026-namaa-arguard">
<titleInfo>
<title>NAMAA at ArGuard Shared Tasks: Multimodal Fusion, Vision–Language Model Adaptation, and In-Context Prompting for Arabic Hateful Meme Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdelbasset</namePart>
<namePart type="family">Djamai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khloud</namePart>
<namePart type="family">Al Jallad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fatimah</namePart>
<namePart type="family">Mohamed Emad Elden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Nacar</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>Multimodal hate speech detection requires interpreting how an image and its accompanying text jointly construct a target, stance, or derogatory implication. In Arabic memes, this relation is often shaped by locally recognizable public figures, political references, visual analogies, and indirect humor, making either modality insufficient on its own. We tackle this problem in Track A of ArGuard 2026, covering binary hateful meme detection (A1) and fine-grained multi-label classification (A2). Our experiments compare jointly trained dual encoders, parameter-efficient vision–language model (VLM) adaptation, and training-free prompting. We fine-tune Qwen3-VL, Llama 3.2 Vision, and Gemma 4 with QLoRA using task-specific binary and multi-label objectives. We also build CLIP–MARBERTv2 and SigLIP–AraBERT-Twitter cross-attention systems and evaluate frozen VLMs with zero-shot prompting and in-context learning. Qwen3-VL achieves our highest A1 score (0.7610), while SigLIP–AraBERT-Twitter leads A2 (0.3851), where label sparsity and multi-label prediction remain challenging.</abstract>
<identifier type="citekey">djamai-etal-2026-namaa-arguard</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.62/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>470</start>
<end>483</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NAMAA at ArGuard Shared Tasks: Multimodal Fusion, Vision–Language Model Adaptation, and In-Context Prompting for Arabic Hateful Meme Detection
%A Djamai, Abdelbasset
%A Al Jallad, Khloud
%A Mohamed Emad Elden, Fatimah
%A Nacar, Omer
%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 djamai-etal-2026-namaa-arguard
%X Multimodal hate speech detection requires interpreting how an image and its accompanying text jointly construct a target, stance, or derogatory implication. In Arabic memes, this relation is often shaped by locally recognizable public figures, political references, visual analogies, and indirect humor, making either modality insufficient on its own. We tackle this problem in Track A of ArGuard 2026, covering binary hateful meme detection (A1) and fine-grained multi-label classification (A2). Our experiments compare jointly trained dual encoders, parameter-efficient vision–language model (VLM) adaptation, and training-free prompting. We fine-tune Qwen3-VL, Llama 3.2 Vision, and Gemma 4 with QLoRA using task-specific binary and multi-label objectives. We also build CLIP–MARBERTv2 and SigLIP–AraBERT-Twitter cross-attention systems and evaluate frozen VLMs with zero-shot prompting and in-context learning. Qwen3-VL achieves our highest A1 score (0.7610), while SigLIP–AraBERT-Twitter leads A2 (0.3851), where label sparsity and multi-label prediction remain challenging.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.62/
%P 470-483
Markdown (Informal)
[NAMAA at ArGuard Shared Tasks: Multimodal Fusion, Vision–Language Model Adaptation, and In-Context Prompting for Arabic Hateful Meme Detection](https://aclanthology.org/2026.arabicnlp-sharedtasks.62/) (Djamai et al., ArabicNLP 2026)
ACL