@inproceedings{alnuwaiser-etal-2026-natural,
title = "Natural, Synthetic, or Mixed Supervision for Open-Weight {A}rabic Grammatical Error Correction",
author = "Alnuwaiser, Mohammed and
Albalawi, Mohammed and
Alghamdi, Thikra Mansoor",
editor = "Adelani, David Ifeoluwa and
Alabi, Jesujoba and
Arnett, Catherine and
Chang, Tyler and
Downey, C.M. and
Goldman, Omer and
Li, Senyu and
Miranda, Lester James Validad and
Qi, Jirui and
Stap, David and
Winata, Genta Indra and
Zhang, Xinyu Crystina",
booktitle = "Proceedings of the 6th Workshop on Multilingual Representation Learning ({MRL} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mrl-1.17/",
pages = "221--229",
ISBN = "979-8-89176-469-9",
abstract = "Modern Standard Arabic grammatical error correction (GEC) remains underexplored for open-weight instruction-tuned large language models (LLMs). We compare natural, synthetic, and mixed training views for a highlighted-token correction task while holding the model, training-set size, and evaluation protocol fixed. We fine-tune Gemma 3 4B with QLoRA on three equal 2,000-record views and evaluate once on 511 Nahw-Passage records. Mixed supervision reaches 31.70{\%} exact-match accuracy, compared with 20.55{\%} for synthetic-only and 28.38{\%} for natural-only; the mixed{--}natural difference is not established. Post-hoc robustness analyses preserve the mixed-over-synthetic direction, but checkpoint selection enlarges its measured size. Auxiliary diagnostics reveal a trade-off: synthetic-only changes fewer already-correct tokens, whereas mixed supervision retains more ArabicMMLU capability. The result concerns these particular data views: source also varies with domain, length, and error distribution; correction quality was not independently assessed. One model and strict single-reference scoring further limit generality."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alnuwaiser-etal-2026-natural">
<titleInfo>
<title>Natural, Synthetic, or Mixed Supervision for Open-Weight Arabic Grammatical Error Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Alnuwaiser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Albalawi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thikra</namePart>
<namePart type="given">Mansoor</namePart>
<namePart type="family">Alghamdi</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 6th Workshop on Multilingual Representation Learning (MRL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesujoba</namePart>
<namePart type="family">Alabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Arnett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Downey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Goldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lester</namePart>
<namePart type="given">James</namePart>
<namePart type="given">Validad</namePart>
<namePart type="family">Miranda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jirui</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Stap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="given">Crystina</namePart>
<namePart type="family">Zhang</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">979-8-89176-469-9</identifier>
</relatedItem>
<abstract>Modern Standard Arabic grammatical error correction (GEC) remains underexplored for open-weight instruction-tuned large language models (LLMs). We compare natural, synthetic, and mixed training views for a highlighted-token correction task while holding the model, training-set size, and evaluation protocol fixed. We fine-tune Gemma 3 4B with QLoRA on three equal 2,000-record views and evaluate once on 511 Nahw-Passage records. Mixed supervision reaches 31.70% exact-match accuracy, compared with 20.55% for synthetic-only and 28.38% for natural-only; the mixed–natural difference is not established. Post-hoc robustness analyses preserve the mixed-over-synthetic direction, but checkpoint selection enlarges its measured size. Auxiliary diagnostics reveal a trade-off: synthetic-only changes fewer already-correct tokens, whereas mixed supervision retains more ArabicMMLU capability. The result concerns these particular data views: source also varies with domain, length, and error distribution; correction quality was not independently assessed. One model and strict single-reference scoring further limit generality.</abstract>
<identifier type="citekey">alnuwaiser-etal-2026-natural</identifier>
<location>
<url>https://aclanthology.org/2026.mrl-1.17/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>221</start>
<end>229</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Natural, Synthetic, or Mixed Supervision for Open-Weight Arabic Grammatical Error Correction
%A Alnuwaiser, Mohammed
%A Albalawi, Mohammed
%A Alghamdi, Thikra Mansoor
%Y Adelani, David Ifeoluwa
%Y Alabi, Jesujoba
%Y Arnett, Catherine
%Y Chang, Tyler
%Y Downey, C. M.
%Y Goldman, Omer
%Y Li, Senyu
%Y Miranda, Lester James Validad
%Y Qi, Jirui
%Y Stap, David
%Y Winata, Genta Indra
%Y Zhang, Xinyu Crystina
%S Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-469-9
%F alnuwaiser-etal-2026-natural
%X Modern Standard Arabic grammatical error correction (GEC) remains underexplored for open-weight instruction-tuned large language models (LLMs). We compare natural, synthetic, and mixed training views for a highlighted-token correction task while holding the model, training-set size, and evaluation protocol fixed. We fine-tune Gemma 3 4B with QLoRA on three equal 2,000-record views and evaluate once on 511 Nahw-Passage records. Mixed supervision reaches 31.70% exact-match accuracy, compared with 20.55% for synthetic-only and 28.38% for natural-only; the mixed–natural difference is not established. Post-hoc robustness analyses preserve the mixed-over-synthetic direction, but checkpoint selection enlarges its measured size. Auxiliary diagnostics reveal a trade-off: synthetic-only changes fewer already-correct tokens, whereas mixed supervision retains more ArabicMMLU capability. The result concerns these particular data views: source also varies with domain, length, and error distribution; correction quality was not independently assessed. One model and strict single-reference scoring further limit generality.
%U https://aclanthology.org/2026.mrl-1.17/
%P 221-229
Markdown (Informal)
[Natural, Synthetic, or Mixed Supervision for Open-Weight Arabic Grammatical Error Correction](https://aclanthology.org/2026.mrl-1.17/) (Alnuwaiser et al., MRL 2026)
ACL