@inproceedings{sheikh-2026-calibguard,
title = "{C}alib{G}uard at {A}r{G}uard Shared Tasks: Threshold Calibration and Label-Space Constraints for {A}rabic Multimodal Hate Speech and Harmful Prompt Detection",
author = "Sheikh, Md. Faisal",
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.47/",
pages = "379--385",
ISBN = "979-8-89176-497-2",
abstract = "This paper describes CalibGuard, our system for the ArGuard 2026 Shared Task on harmful content detection in Arabic memes and large language model prompts. We participate in all four subtasks: binary and fine-grained hateful meme classification (A1, A2) and binary and harm-domain prompt classification (B1, B2). For Task A, we extract frozen embeddings from three vision-text encoder pairs and train a joint two-headed classifier under 5-fold cross-validation with seed averaging. For Task B, we fine-tune AraBERTv02 with class-weighted cross-entropy. CalibGuard obtains 75.53{\%} macro-F1 on subtask A1, 36.53{\%} on A2, 65.38{\%} on B1 and 68.85{\%} on B2, ranking 11th, 3rd, 15th and 13th respectively. We further show that the B1 test split contains 49.3{\%} unsafe prompts against 79.8{\%} in training, and that this distribution shift accounts for a 29-point gap between our development and test scores, concentrated entirely in Modern Standard Arabic. Rethresholding to the test prior recovers 13.7 points without retraining. We additionally report two negative results: constrained decoding marginally reduces A2 performance, and restricting B2 training to unsafe prompts costs 5.7 points."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sheikh-2026-calibguard">
<titleInfo>
<title>CalibGuard at ArGuard Shared Tasks: Threshold Calibration and Label-Space Constraints for Arabic Multimodal Hate Speech and Harmful Prompt Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Faisal</namePart>
<namePart type="family">Sheikh</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>This paper describes CalibGuard, our system for the ArGuard 2026 Shared Task on harmful content detection in Arabic memes and large language model prompts. We participate in all four subtasks: binary and fine-grained hateful meme classification (A1, A2) and binary and harm-domain prompt classification (B1, B2). For Task A, we extract frozen embeddings from three vision-text encoder pairs and train a joint two-headed classifier under 5-fold cross-validation with seed averaging. For Task B, we fine-tune AraBERTv02 with class-weighted cross-entropy. CalibGuard obtains 75.53% macro-F1 on subtask A1, 36.53% on A2, 65.38% on B1 and 68.85% on B2, ranking 11th, 3rd, 15th and 13th respectively. We further show that the B1 test split contains 49.3% unsafe prompts against 79.8% in training, and that this distribution shift accounts for a 29-point gap between our development and test scores, concentrated entirely in Modern Standard Arabic. Rethresholding to the test prior recovers 13.7 points without retraining. We additionally report two negative results: constrained decoding marginally reduces A2 performance, and restricting B2 training to unsafe prompts costs 5.7 points.</abstract>
<identifier type="citekey">sheikh-2026-calibguard</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.47/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>379</start>
<end>385</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CalibGuard at ArGuard Shared Tasks: Threshold Calibration and Label-Space Constraints for Arabic Multimodal Hate Speech and Harmful Prompt Detection
%A Sheikh, Md. Faisal
%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 sheikh-2026-calibguard
%X This paper describes CalibGuard, our system for the ArGuard 2026 Shared Task on harmful content detection in Arabic memes and large language model prompts. We participate in all four subtasks: binary and fine-grained hateful meme classification (A1, A2) and binary and harm-domain prompt classification (B1, B2). For Task A, we extract frozen embeddings from three vision-text encoder pairs and train a joint two-headed classifier under 5-fold cross-validation with seed averaging. For Task B, we fine-tune AraBERTv02 with class-weighted cross-entropy. CalibGuard obtains 75.53% macro-F1 on subtask A1, 36.53% on A2, 65.38% on B1 and 68.85% on B2, ranking 11th, 3rd, 15th and 13th respectively. We further show that the B1 test split contains 49.3% unsafe prompts against 79.8% in training, and that this distribution shift accounts for a 29-point gap between our development and test scores, concentrated entirely in Modern Standard Arabic. Rethresholding to the test prior recovers 13.7 points without retraining. We additionally report two negative results: constrained decoding marginally reduces A2 performance, and restricting B2 training to unsafe prompts costs 5.7 points.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.47/
%P 379-385
Markdown (Informal)
[CalibGuard at ArGuard Shared Tasks: Threshold Calibration and Label-Space Constraints for Arabic Multimodal Hate Speech and Harmful Prompt Detection](https://aclanthology.org/2026.arabicnlp-sharedtasks.47/) (Sheikh, ArabicNLP 2026)
ACL