@inproceedings{rishta-zaman-2026-nile,
title = "Nile Nexus at {A}r{G}uard Shared Tasks: Leakage-Controlled {MARBERT}v2{--}{SVM} Ensemble for {A}rabic Harmful-Prompt Classification",
author = "Rishta, Miftahul Jannat and
Zaman, Sumaiya",
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.41/",
pages = "332--337",
ISBN = "979-8-89176-497-2",
abstract = "Arabic harmful-prompt detection has remained challenging due to dialectal variation, implicit expressions and context-dependent intent. In the ArGuard 2026 Shared Task, we have participated in Subtask B1, a binary safe/unsafe classification task scored by macro-F1. We have identified evaluation leakage in an initial pipeline: the development set has been reused for early stopping, threshold tuning and ensemble optimization, which has inflated development scores while masking poor generalization on the blind test set. To correct this, we have introduced a leakage-controlled protocol with separate fitting, checkpoint-selection and tuning splits and have compared a TF-IDF SVM baseline, MARBERTv2 and a stacking ensemble, selecting the best-performing method based on tuning-set results. We have further applied five rounds of error-driven data augmentation to address recurring failure patterns. Our final system has achieved 0.861 accuracy, 0.878 precision, 0.862 recall and 0.860 macro-F1 on the blind test leaderboard, ranking 5th. Manual error analysis has shown that remaining errors have mainly stemmed from false positives on sensitive but non-harmful content, confirming that leakage-controlled evaluation has been necessary for a reliable blind-test estimate."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rishta-zaman-2026-nile">
<titleInfo>
<title>Nile Nexus at ArGuard Shared Tasks: Leakage-Controlled MARBERTv2–SVM Ensemble for Arabic Harmful-Prompt Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miftahul</namePart>
<namePart type="given">Jannat</namePart>
<namePart type="family">Rishta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sumaiya</namePart>
<namePart type="family">Zaman</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>Arabic harmful-prompt detection has remained challenging due to dialectal variation, implicit expressions and context-dependent intent. In the ArGuard 2026 Shared Task, we have participated in Subtask B1, a binary safe/unsafe classification task scored by macro-F1. We have identified evaluation leakage in an initial pipeline: the development set has been reused for early stopping, threshold tuning and ensemble optimization, which has inflated development scores while masking poor generalization on the blind test set. To correct this, we have introduced a leakage-controlled protocol with separate fitting, checkpoint-selection and tuning splits and have compared a TF-IDF SVM baseline, MARBERTv2 and a stacking ensemble, selecting the best-performing method based on tuning-set results. We have further applied five rounds of error-driven data augmentation to address recurring failure patterns. Our final system has achieved 0.861 accuracy, 0.878 precision, 0.862 recall and 0.860 macro-F1 on the blind test leaderboard, ranking 5th. Manual error analysis has shown that remaining errors have mainly stemmed from false positives on sensitive but non-harmful content, confirming that leakage-controlled evaluation has been necessary for a reliable blind-test estimate.</abstract>
<identifier type="citekey">rishta-zaman-2026-nile</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.41/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>332</start>
<end>337</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Nile Nexus at ArGuard Shared Tasks: Leakage-Controlled MARBERTv2–SVM Ensemble for Arabic Harmful-Prompt Classification
%A Rishta, Miftahul Jannat
%A Zaman, Sumaiya
%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 rishta-zaman-2026-nile
%X Arabic harmful-prompt detection has remained challenging due to dialectal variation, implicit expressions and context-dependent intent. In the ArGuard 2026 Shared Task, we have participated in Subtask B1, a binary safe/unsafe classification task scored by macro-F1. We have identified evaluation leakage in an initial pipeline: the development set has been reused for early stopping, threshold tuning and ensemble optimization, which has inflated development scores while masking poor generalization on the blind test set. To correct this, we have introduced a leakage-controlled protocol with separate fitting, checkpoint-selection and tuning splits and have compared a TF-IDF SVM baseline, MARBERTv2 and a stacking ensemble, selecting the best-performing method based on tuning-set results. We have further applied five rounds of error-driven data augmentation to address recurring failure patterns. Our final system has achieved 0.861 accuracy, 0.878 precision, 0.862 recall and 0.860 macro-F1 on the blind test leaderboard, ranking 5th. Manual error analysis has shown that remaining errors have mainly stemmed from false positives on sensitive but non-harmful content, confirming that leakage-controlled evaluation has been necessary for a reliable blind-test estimate.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.41/
%P 332-337
Markdown (Informal)
[Nile Nexus at ArGuard Shared Tasks: Leakage-Controlled MARBERTv2–SVM Ensemble for Arabic Harmful-Prompt Classification](https://aclanthology.org/2026.arabicnlp-sharedtasks.41/) (Rishta & Zaman, ArabicNLP 2026)
ACL