@inproceedings{al-madi-2026-lsi,
title = "{LSI} at {BAREC} Shared Task 2026: A Controlled Study of Training Convergence, Heuristics, and Ensembles for {A}rabic Sentence-Level Readability",
author = "Al-Madi, Sahara H.",
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.25/",
pages = "219--224",
ISBN = "979-8-89176-497-2",
abstract = "We present the Linguistic Security Institute (LSI) submission to the BAREC Shared Task 2026 (Task 1): predicting Arabic sentence readability on a 19-level ordinal scale. Our approach uses a logit-level ensemble of three Arabic pre-trained language models, with CAMeLBERT trained using an ordinal Earth Mover{'}s Distance loss and augmented by six SAMER Lexicon difficulty features. Controlled comparisons show that surface heuristics improve undertrained baselines but degrade converged models, and retrieval-augmented in-context learning yields no gains in this fine-grained setting. Our final ensemble achieves 81.7 QWK, ranking 1st among Constrained-track system submissions and 3rd among Open-track system submissions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-madi-2026-lsi">
<titleInfo>
<title>LSI at BAREC Shared Task 2026: A Controlled Study of Training Convergence, Heuristics, and Ensembles for Arabic Sentence-Level Readability</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sahara</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Al-Madi</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 present the Linguistic Security Institute (LSI) submission to the BAREC Shared Task 2026 (Task 1): predicting Arabic sentence readability on a 19-level ordinal scale. Our approach uses a logit-level ensemble of three Arabic pre-trained language models, with CAMeLBERT trained using an ordinal Earth Mover’s Distance loss and augmented by six SAMER Lexicon difficulty features. Controlled comparisons show that surface heuristics improve undertrained baselines but degrade converged models, and retrieval-augmented in-context learning yields no gains in this fine-grained setting. Our final ensemble achieves 81.7 QWK, ranking 1st among Constrained-track system submissions and 3rd among Open-track system submissions.</abstract>
<identifier type="citekey">al-madi-2026-lsi</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.25/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>219</start>
<end>224</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LSI at BAREC Shared Task 2026: A Controlled Study of Training Convergence, Heuristics, and Ensembles for Arabic Sentence-Level Readability
%A Al-Madi, Sahara H.
%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 al-madi-2026-lsi
%X We present the Linguistic Security Institute (LSI) submission to the BAREC Shared Task 2026 (Task 1): predicting Arabic sentence readability on a 19-level ordinal scale. Our approach uses a logit-level ensemble of three Arabic pre-trained language models, with CAMeLBERT trained using an ordinal Earth Mover’s Distance loss and augmented by six SAMER Lexicon difficulty features. Controlled comparisons show that surface heuristics improve undertrained baselines but degrade converged models, and retrieval-augmented in-context learning yields no gains in this fine-grained setting. Our final ensemble achieves 81.7 QWK, ranking 1st among Constrained-track system submissions and 3rd among Open-track system submissions.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.25/
%P 219-224
Markdown (Informal)
[LSI at BAREC Shared Task 2026: A Controlled Study of Training Convergence, Heuristics, and Ensembles for Arabic Sentence-Level Readability](https://aclanthology.org/2026.arabicnlp-sharedtasks.25/) (Al-Madi, ArabicNLP 2026)
ACL