@inproceedings{ojo-etal-2026-nlplab,
title = "{NLPL}ab at {A}r{G}uard Shared Tasks: Balancing Confidence Scores for Fine-Grained Classification of Unsafe {A}rabic Prompts Across Harm Domains",
author = "Ojo, Olumide Ebenezer and
Ogunlenu, Hamid T. and
Adebanji, Olaronke Oluwayemisi and
Abiola, Tolulope Olalekan and
Calvo, Hiram and
Gelbukh, Alexander",
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.56/",
pages = "437--442",
ISBN = "979-8-89176-497-2",
abstract = "This paper presents the CIC system for ArGuard 2026 Subtask B2, which classifies unsafe Arabic prompts into one of seven harm domains. Our system combines four complementary components: a fine-tuned CAMeLBERT-Mix model, a modified-Huber stochastic gradient descent classifier, a character-level nearest-neighbor model, and a character class-centroid similarity model. On the development set, we achieved a Macro-F1 score of 0.916 and an accuracy of 0.923. On the test set, the proposed model achieved an accuracy of \textbf{0.766}, a macro precision of \textbf{0.760}, a macro recall of \textbf{0.763}, and a Macro-F1 of \textbf{0.751}. The results show that combining contextual transformer representations, lexical features, and retrieval-based similarity signals can improve fine-grained harmful-prompt classification."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ojo-etal-2026-nlplab">
<titleInfo>
<title>NLPLab at ArGuard Shared Tasks: Balancing Confidence Scores for Fine-Grained Classification of Unsafe Arabic Prompts Across Harm Domains</title>
</titleInfo>
<name type="personal">
<namePart type="given">Olumide</namePart>
<namePart type="given">Ebenezer</namePart>
<namePart type="family">Ojo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamid</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Ogunlenu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olaronke</namePart>
<namePart type="given">Oluwayemisi</namePart>
<namePart type="family">Adebanji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tolulope</namePart>
<namePart type="given">Olalekan</namePart>
<namePart type="family">Abiola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiram</namePart>
<namePart type="family">Calvo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Gelbukh</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 the CIC system for ArGuard 2026 Subtask B2, which classifies unsafe Arabic prompts into one of seven harm domains. Our system combines four complementary components: a fine-tuned CAMeLBERT-Mix model, a modified-Huber stochastic gradient descent classifier, a character-level nearest-neighbor model, and a character class-centroid similarity model. On the development set, we achieved a Macro-F1 score of 0.916 and an accuracy of 0.923. On the test set, the proposed model achieved an accuracy of 0.766, a macro precision of 0.760, a macro recall of 0.763, and a Macro-F1 of 0.751. The results show that combining contextual transformer representations, lexical features, and retrieval-based similarity signals can improve fine-grained harmful-prompt classification.</abstract>
<identifier type="citekey">ojo-etal-2026-nlplab</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.56/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>437</start>
<end>442</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLPLab at ArGuard Shared Tasks: Balancing Confidence Scores for Fine-Grained Classification of Unsafe Arabic Prompts Across Harm Domains
%A Ojo, Olumide Ebenezer
%A Ogunlenu, Hamid T.
%A Adebanji, Olaronke Oluwayemisi
%A Abiola, Tolulope Olalekan
%A Calvo, Hiram
%A Gelbukh, Alexander
%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 ojo-etal-2026-nlplab
%X This paper presents the CIC system for ArGuard 2026 Subtask B2, which classifies unsafe Arabic prompts into one of seven harm domains. Our system combines four complementary components: a fine-tuned CAMeLBERT-Mix model, a modified-Huber stochastic gradient descent classifier, a character-level nearest-neighbor model, and a character class-centroid similarity model. On the development set, we achieved a Macro-F1 score of 0.916 and an accuracy of 0.923. On the test set, the proposed model achieved an accuracy of 0.766, a macro precision of 0.760, a macro recall of 0.763, and a Macro-F1 of 0.751. The results show that combining contextual transformer representations, lexical features, and retrieval-based similarity signals can improve fine-grained harmful-prompt classification.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.56/
%P 437-442
Markdown (Informal)
[NLPLab at ArGuard Shared Tasks: Balancing Confidence Scores for Fine-Grained Classification of Unsafe Arabic Prompts Across Harm Domains](https://aclanthology.org/2026.arabicnlp-sharedtasks.56/) (Ojo et al., ArabicNLP 2026)
ACL