@inproceedings{albatarni-etal-2026-fine,
title = "Fine-tuning Small Language Models for Cross-Prompt {A}rabic Essay Scoring: A Benchmarking Study",
author = "Albatarni, Salam and
Dalvi, Fahim and
Eltanbouly, Sohaila and
Elsayed, Tamer",
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",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-main.2/",
pages = "11--21",
ISBN = "979-8-89176-473-6",
abstract = "Automated Essay Scoring (AES) has been studied since the early days of computational methods. While recent advances incorporating large language models (LLMs) have significantly improved performance, most research has focused on English. In this paper, we present the first benchmark of Arabic cross-prompt AES using Arabic-centric LLMs. We evaluate ALLaM 7B, Jais 8B, and Fanar 9B under zero-shot, few-shot, and fine-tuning settings, and compare them against established AES systems and frontier LLMs. Fine-tuning substantially improves performance across all models, with Fanar achieving state-of-the-art results and outperforming the strongest baseline by 8 points on LAILA dataset. We further show that fine-tuned Arabic-centric LLMs generalize effectively in cross-dataset setting (LAILA $\rightarrow$ ZAEBUC). Finally, we analyze the best-performing model, examining error patterns, trait interactions, and the effects of multi-trait autoregressive scoring."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="albatarni-etal-2026-fine">
<titleInfo>
<title>Fine-tuning Small Language Models for Cross-Prompt Arabic Essay Scoring: A Benchmarking Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Albatarni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fahim</namePart>
<namePart type="family">Dalvi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sohaila</namePart>
<namePart type="family">Eltanbouly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</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</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">979-8-89176-473-6</identifier>
</relatedItem>
<abstract>Automated Essay Scoring (AES) has been studied since the early days of computational methods. While recent advances incorporating large language models (LLMs) have significantly improved performance, most research has focused on English. In this paper, we present the first benchmark of Arabic cross-prompt AES using Arabic-centric LLMs. We evaluate ALLaM 7B, Jais 8B, and Fanar 9B under zero-shot, few-shot, and fine-tuning settings, and compare them against established AES systems and frontier LLMs. Fine-tuning substantially improves performance across all models, with Fanar achieving state-of-the-art results and outperforming the strongest baseline by 8 points on LAILA dataset. We further show that fine-tuned Arabic-centric LLMs generalize effectively in cross-dataset setting (LAILA \rightarrow ZAEBUC). Finally, we analyze the best-performing model, examining error patterns, trait interactions, and the effects of multi-trait autoregressive scoring.</abstract>
<identifier type="citekey">albatarni-etal-2026-fine</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-main.2/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>11</start>
<end>21</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-tuning Small Language Models for Cross-Prompt Arabic Essay Scoring: A Benchmarking Study
%A Albatarni, Salam
%A Dalvi, Fahim
%A Eltanbouly, Sohaila
%A Elsayed, Tamer
%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
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-473-6
%F albatarni-etal-2026-fine
%X Automated Essay Scoring (AES) has been studied since the early days of computational methods. While recent advances incorporating large language models (LLMs) have significantly improved performance, most research has focused on English. In this paper, we present the first benchmark of Arabic cross-prompt AES using Arabic-centric LLMs. We evaluate ALLaM 7B, Jais 8B, and Fanar 9B under zero-shot, few-shot, and fine-tuning settings, and compare them against established AES systems and frontier LLMs. Fine-tuning substantially improves performance across all models, with Fanar achieving state-of-the-art results and outperforming the strongest baseline by 8 points on LAILA dataset. We further show that fine-tuned Arabic-centric LLMs generalize effectively in cross-dataset setting (LAILA \rightarrow ZAEBUC). Finally, we analyze the best-performing model, examining error patterns, trait interactions, and the effects of multi-trait autoregressive scoring.
%U https://aclanthology.org/2026.arabicnlp-main.2/
%P 11-21
Markdown (Informal)
[Fine-tuning Small Language Models for Cross-Prompt Arabic Essay Scoring: A Benchmarking Study](https://aclanthology.org/2026.arabicnlp-main.2/) (Albatarni et al., ArabicNLP 2026)
ACL