@inproceedings{muntaha-etal-2026-quadcore,
title = "{Q}uad{C}ore at {A}r{G}uard Shared Tasks: Ensembling {A}rabic Encoders with Dialect Conditioning for Harm-Domain Classification",
author = "Muntaha, Sidratul and
Anzum, Sabila and
Tonny, Umme Saima and
Tabassum, Maimuna",
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.53/",
pages = "419--425",
ISBN = "979-8-89176-497-2",
abstract = "We describe the QuadCore submission to Sub task B2 of the ArGuard 2026 shared task, which asks systems to assign an Arabic prompt addressed to a large language model to one of seven harm domains. Our system is a soft-voting ensemble of three Arabic en coders with complementary pre-training cor pora- MARBERTv2, CAMeLBERT-DA and AraBERTv02-Twitter- each fine-tuned under two random seeds, with the annotated dialect prepended to the prompt as a textual condition ing prefix; it uses no external data, no augmen tation and no generative models. It reached 0.7665 macro-F1 on the official test set, rank ing 4th of the 16 teams that submitted to the subtask. Using the gold labels released after the evaluation period, we then show that this sin gle number conflates two regimes: on the first 4,809 test items, whose label prior, dialect mix and lexical profile match the training data, the same predictions reach 0.9044 macro-F1, while on a contiguous final block of 1,170 items they collapse to 0.2073. That block is entirely Mod ern Standard Arabic, contains no adult-content instance, and its nearest-neighbour label agree ment with the training set is 0.1829 against 0.7777 elsewhere- close to the 1/7 chance rate. A substantial portion of our system{'}s errors on the official test set is therefore attributable to this shift rather than to the difficulty of harm domain classification itself."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="muntaha-etal-2026-quadcore">
<titleInfo>
<title>QuadCore at ArGuard Shared Tasks: Ensembling Arabic Encoders with Dialect Conditioning for Harm-Domain Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sidratul</namePart>
<namePart type="family">Muntaha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabila</namePart>
<namePart type="family">Anzum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Umme</namePart>
<namePart type="given">Saima</namePart>
<namePart type="family">Tonny</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maimuna</namePart>
<namePart type="family">Tabassum</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>We describe the QuadCore submission to Sub task B2 of the ArGuard 2026 shared task, which asks systems to assign an Arabic prompt addressed to a large language model to one of seven harm domains. Our system is a soft-voting ensemble of three Arabic en coders with complementary pre-training cor pora- MARBERTv2, CAMeLBERT-DA and AraBERTv02-Twitter- each fine-tuned under two random seeds, with the annotated dialect prepended to the prompt as a textual condition ing prefix; it uses no external data, no augmen tation and no generative models. It reached 0.7665 macro-F1 on the official test set, rank ing 4th of the 16 teams that submitted to the subtask. Using the gold labels released after the evaluation period, we then show that this sin gle number conflates two regimes: on the first 4,809 test items, whose label prior, dialect mix and lexical profile match the training data, the same predictions reach 0.9044 macro-F1, while on a contiguous final block of 1,170 items they collapse to 0.2073. That block is entirely Mod ern Standard Arabic, contains no adult-content instance, and its nearest-neighbour label agree ment with the training set is 0.1829 against 0.7777 elsewhere- close to the 1/7 chance rate. A substantial portion of our system’s errors on the official test set is therefore attributable to this shift rather than to the difficulty of harm domain classification itself.</abstract>
<identifier type="citekey">muntaha-etal-2026-quadcore</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.53/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>419</start>
<end>425</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QuadCore at ArGuard Shared Tasks: Ensembling Arabic Encoders with Dialect Conditioning for Harm-Domain Classification
%A Muntaha, Sidratul
%A Anzum, Sabila
%A Tonny, Umme Saima
%A Tabassum, Maimuna
%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 muntaha-etal-2026-quadcore
%X We describe the QuadCore submission to Sub task B2 of the ArGuard 2026 shared task, which asks systems to assign an Arabic prompt addressed to a large language model to one of seven harm domains. Our system is a soft-voting ensemble of three Arabic en coders with complementary pre-training cor pora- MARBERTv2, CAMeLBERT-DA and AraBERTv02-Twitter- each fine-tuned under two random seeds, with the annotated dialect prepended to the prompt as a textual condition ing prefix; it uses no external data, no augmen tation and no generative models. It reached 0.7665 macro-F1 on the official test set, rank ing 4th of the 16 teams that submitted to the subtask. Using the gold labels released after the evaluation period, we then show that this sin gle number conflates two regimes: on the first 4,809 test items, whose label prior, dialect mix and lexical profile match the training data, the same predictions reach 0.9044 macro-F1, while on a contiguous final block of 1,170 items they collapse to 0.2073. That block is entirely Mod ern Standard Arabic, contains no adult-content instance, and its nearest-neighbour label agree ment with the training set is 0.1829 against 0.7777 elsewhere- close to the 1/7 chance rate. A substantial portion of our system’s errors on the official test set is therefore attributable to this shift rather than to the difficulty of harm domain classification itself.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.53/
%P 419-425
Markdown (Informal)
[QuadCore at ArGuard Shared Tasks: Ensembling Arabic Encoders with Dialect Conditioning for Harm-Domain Classification](https://aclanthology.org/2026.arabicnlp-sharedtasks.53/) (Muntaha et al., ArabicNLP 2026)
ACL