@inproceedings{mohamed-ajlan-2026-al,
title = "Al-Qahera at {A}rabic Segmentation Shared Task 2026: Genre-Conditioned {LLM} Prompting versus Supervised Multi-Backbone Ensembling",
author = "Mohamed, Mohamed and
Ajlan, Hazem",
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.124/",
pages = "1010--1021",
ISBN = "979-8-89176-497-2",
abstract = "We submit systems to both the closed and open divisions of all four tracks of the AraSeg 2026 shared task (PA, NP, NoPnx-PA, NoPnx-NP): a supervised 3-backbone ensemble (CAMeLBERT-MSA, AraBERTv02, and AraELECTRA, each with a gated-residual head, R-Drop regularization, and stochastic weight averaging), and a zero-shot LLM system prompted with explicit, track-specific segmentation rules instead of labeled examples. The ensemble uses no external resources, so it is entered in both divisions everywhere; for NoPnx-NP specifically, where every structural cue is stripped away, we additionally blend its predictions with the LLM system{'}s, in a real-data-only variant (closed-eligible) and a wiki-augmented variant trained with added pseudo-labeled Wikipedia data (open-only). On the officially-scored blind test, our best submission per track reaches 94.70 $F_1$ (PA), 91.00 (NP), 91.20 (NoPnx-PA), and 87.40 (NoPnx-NP). The supervised ensemble is the stronger, more consistent choice overall; the one exception is NoPnx-PA, where our LLM system{'}s unmodified seed prompt outperforms it and combining the two systems does not help{---}the only track where that happens. We report in full the structural annotation ambiguities we uncovered while building the LLM system."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohamed-ajlan-2026-al">
<titleInfo>
<title>Al-Qahera at Arabic Segmentation Shared Task 2026: Genre-Conditioned LLM Prompting versus Supervised Multi-Backbone Ensembling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hazem</namePart>
<namePart type="family">Ajlan</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 submit systems to both the closed and open divisions of all four tracks of the AraSeg 2026 shared task (PA, NP, NoPnx-PA, NoPnx-NP): a supervised 3-backbone ensemble (CAMeLBERT-MSA, AraBERTv02, and AraELECTRA, each with a gated-residual head, R-Drop regularization, and stochastic weight averaging), and a zero-shot LLM system prompted with explicit, track-specific segmentation rules instead of labeled examples. The ensemble uses no external resources, so it is entered in both divisions everywhere; for NoPnx-NP specifically, where every structural cue is stripped away, we additionally blend its predictions with the LLM system’s, in a real-data-only variant (closed-eligible) and a wiki-augmented variant trained with added pseudo-labeled Wikipedia data (open-only). On the officially-scored blind test, our best submission per track reaches 94.70 F₁ (PA), 91.00 (NP), 91.20 (NoPnx-PA), and 87.40 (NoPnx-NP). The supervised ensemble is the stronger, more consistent choice overall; the one exception is NoPnx-PA, where our LLM system’s unmodified seed prompt outperforms it and combining the two systems does not help—the only track where that happens. We report in full the structural annotation ambiguities we uncovered while building the LLM system.</abstract>
<identifier type="citekey">mohamed-ajlan-2026-al</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.124/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1010</start>
<end>1021</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings %T Al-Qahera at Arabic Segmentation Shared Task 2026: Genre-Conditioned LLM Prompting versus Supervised Multi-Backbone Ensembling %A Mohamed, Mohamed %A Ajlan, Hazem %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 mohamed-ajlan-2026-al %X We submit systems to both the closed and open divisions of all four tracks of the AraSeg 2026 shared task (PA, NP, NoPnx-PA, NoPnx-NP): a supervised 3-backbone ensemble (CAMeLBERT-MSA, AraBERTv02, and AraELECTRA, each with a gated-residual head, R-Drop regularization, and stochastic weight averaging), and a zero-shot LLM system prompted with explicit, track-specific segmentation rules instead of labeled examples. The ensemble uses no external resources, so it is entered in both divisions everywhere; for NoPnx-NP specifically, where every structural cue is stripped away, we additionally blend its predictions with the LLM system’s, in a real-data-only variant (closed-eligible) and a wiki-augmented variant trained with added pseudo-labeled Wikipedia data (open-only). On the officially-scored blind test, our best submission per track reaches 94.70 F₁ (PA), 91.00 (NP), 91.20 (NoPnx-PA), and 87.40 (NoPnx-NP). The supervised ensemble is the stronger, more consistent choice overall; the one exception is NoPnx-PA, where our LLM system’s unmodified seed prompt outperforms it and combining the two systems does not help—the only track where that happens. We report in full the structural annotation ambiguities we uncovered while building the LLM system. %U https://aclanthology.org/2026.arabicnlp-sharedtasks.124/ %P 1010-1021
Markdown (Informal)
[Al-Qahera at Arabic Segmentation Shared Task 2026: Genre-Conditioned LLM Prompting versus Supervised Multi-Backbone Ensembling](https://aclanthology.org/2026.arabicnlp-sharedtasks.124/) (Mohamed & Ajlan, ArabicNLP 2026)