@inproceedings{bestgen-2026-satlab-arguard,
title = "{SATL}ab at {A}r{G}uard Shared Tasks: Character N-Grams for Fine-Grained Categorization of Harmful {LLM} Prompts in {A}rabic",
author = "Bestgen, Yves",
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.52/",
pages = "413--418",
ISBN = "979-8-89176-497-2",
abstract = "This paper presents SATLab{'}s participation in the ArGuard 2026 shared sub-task on identifying seven types of harmful LLM prompts in Arabic. The proposed system is language-agnostic and requires no resources other than the training data provided in the shared task. It is based on character n-grams and a logistic regression classifier. Performance on the Test set (Macro-F1 = 0.736) was average, approximately 0.05 lower than that of the top teams (0.790) and approximately 0.05 higher than the baseline (0.687). Notably, this performance was substantially lower than those achieved in cross-validation and on the Development set. Several analyses aimed at understanding these discrepancies are reported. An analysis of the confusion matrix indicates that the ``Harm-to-other'' category poses the greatest problem, likely because it is partially compatible with all other categories except ``Adult-content''."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bestgen-2026-satlab-arguard">
<titleInfo>
<title>SATLab at ArGuard Shared Tasks: Character N-Grams for Fine-Grained Categorization of Harmful LLM Prompts in Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Bestgen</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 presents SATLab’s participation in the ArGuard 2026 shared sub-task on identifying seven types of harmful LLM prompts in Arabic. The proposed system is language-agnostic and requires no resources other than the training data provided in the shared task. It is based on character n-grams and a logistic regression classifier. Performance on the Test set (Macro-F1 = 0.736) was average, approximately 0.05 lower than that of the top teams (0.790) and approximately 0.05 higher than the baseline (0.687). Notably, this performance was substantially lower than those achieved in cross-validation and on the Development set. Several analyses aimed at understanding these discrepancies are reported. An analysis of the confusion matrix indicates that the “Harm-to-other” category poses the greatest problem, likely because it is partially compatible with all other categories except “Adult-content”.</abstract>
<identifier type="citekey">bestgen-2026-satlab-arguard</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.52/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>413</start>
<end>418</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SATLab at ArGuard Shared Tasks: Character N-Grams for Fine-Grained Categorization of Harmful LLM Prompts in Arabic
%A Bestgen, Yves
%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 bestgen-2026-satlab-arguard
%X This paper presents SATLab’s participation in the ArGuard 2026 shared sub-task on identifying seven types of harmful LLM prompts in Arabic. The proposed system is language-agnostic and requires no resources other than the training data provided in the shared task. It is based on character n-grams and a logistic regression classifier. Performance on the Test set (Macro-F1 = 0.736) was average, approximately 0.05 lower than that of the top teams (0.790) and approximately 0.05 higher than the baseline (0.687). Notably, this performance was substantially lower than those achieved in cross-validation and on the Development set. Several analyses aimed at understanding these discrepancies are reported. An analysis of the confusion matrix indicates that the “Harm-to-other” category poses the greatest problem, likely because it is partially compatible with all other categories except “Adult-content”.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.52/
%P 413-418
Markdown (Informal)
[SATLab at ArGuard Shared Tasks: Character N-Grams for Fine-Grained Categorization of Harmful LLM Prompts in Arabic](https://aclanthology.org/2026.arabicnlp-sharedtasks.52/) (Bestgen, ArabicNLP 2026)
ACL