@inproceedings{ben-chaabane-etal-2026-anlp-uniso,
title = "{ANLP}-{U}ni{S}o at {A}r{G}uard 2026 Task {B}: Multi-Task {MARBERT} with Focal Loss and Hierarchical Consistency for {A}rabic Harmful Prompt Detection",
author = "Ben Chaabane, Saoussen and
Trigui, Omar and
Jaoua, Maher",
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.59/",
pages = "453--457",
ISBN = "979-8-89176-497-2",
abstract = "Detecting harmful prompts directed at large language models is a critical safety challenge, especially in Arabic where dialectal variation, code-switching, and culturally specific expressions of harm complicate classification. The ArGuard 2026 shared task addresses this problem through two subtasks: binary classification of prompts as safe or unsafe (B1) and fine-grained classification of unsafe prompts into seven harm domains (B2). We participate with a multi-task fine-tuning of MARBERT that shares encoder representations across a binary head and a seven-class granular head. Training combines focal loss with class weights and label smoothing, a hierarchical consistency regularizer that discourages contradictory safe/unsafe and granular predictions, a weighted sampler, and light character-level augmentation. On the official development set the system reaches a binary macro-F1 of 0.9618 and a granular macro-F1 of 1.0000; on the blind test set it obtains binary macro-F1 0.688 and granular macro-F1 0.752. We analyse the substantial development{--}test gap and discuss limitations of the submitted system."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ben-chaabane-etal-2026-anlp-uniso">
<titleInfo>
<title>ANLP-UniSo at ArGuard 2026 Task B: Multi-Task MARBERT with Focal Loss and Hierarchical Consistency for Arabic Harmful Prompt Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saoussen</namePart>
<namePart type="family">Ben Chaabane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="family">Trigui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maher</namePart>
<namePart type="family">Jaoua</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>Detecting harmful prompts directed at large language models is a critical safety challenge, especially in Arabic where dialectal variation, code-switching, and culturally specific expressions of harm complicate classification. The ArGuard 2026 shared task addresses this problem through two subtasks: binary classification of prompts as safe or unsafe (B1) and fine-grained classification of unsafe prompts into seven harm domains (B2). We participate with a multi-task fine-tuning of MARBERT that shares encoder representations across a binary head and a seven-class granular head. Training combines focal loss with class weights and label smoothing, a hierarchical consistency regularizer that discourages contradictory safe/unsafe and granular predictions, a weighted sampler, and light character-level augmentation. On the official development set the system reaches a binary macro-F1 of 0.9618 and a granular macro-F1 of 1.0000; on the blind test set it obtains binary macro-F1 0.688 and granular macro-F1 0.752. We analyse the substantial development–test gap and discuss limitations of the submitted system.</abstract>
<identifier type="citekey">ben-chaabane-etal-2026-anlp-uniso</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.59/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>453</start>
<end>457</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ANLP-UniSo at ArGuard 2026 Task B: Multi-Task MARBERT with Focal Loss and Hierarchical Consistency for Arabic Harmful Prompt Detection
%A Ben Chaabane, Saoussen
%A Trigui, Omar
%A Jaoua, Maher
%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 ben-chaabane-etal-2026-anlp-uniso
%X Detecting harmful prompts directed at large language models is a critical safety challenge, especially in Arabic where dialectal variation, code-switching, and culturally specific expressions of harm complicate classification. The ArGuard 2026 shared task addresses this problem through two subtasks: binary classification of prompts as safe or unsafe (B1) and fine-grained classification of unsafe prompts into seven harm domains (B2). We participate with a multi-task fine-tuning of MARBERT that shares encoder representations across a binary head and a seven-class granular head. Training combines focal loss with class weights and label smoothing, a hierarchical consistency regularizer that discourages contradictory safe/unsafe and granular predictions, a weighted sampler, and light character-level augmentation. On the official development set the system reaches a binary macro-F1 of 0.9618 and a granular macro-F1 of 1.0000; on the blind test set it obtains binary macro-F1 0.688 and granular macro-F1 0.752. We analyse the substantial development–test gap and discuss limitations of the submitted system.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.59/
%P 453-457
Markdown (Informal)
[ANLP-UniSo at ArGuard 2026 Task B: Multi-Task MARBERT with Focal Loss and Hierarchical Consistency for Arabic Harmful Prompt Detection](https://aclanthology.org/2026.arabicnlp-sharedtasks.59/) (Ben Chaabane et al., ArabicNLP 2026)
ACL