YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models

Mahmoud Reda; Salam Khalifa; Reham Marzouk; Nizar Habash

doi:10.18653/2026.findings-emnlp.2035

YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models

Mahmoud Reda, Salam Khalifa, Reham Marzouk, Nizar Habash

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Arabic morphology remains challenging for large language models, since fluent generation does not guarantee accurate morphosyntactic control. Existing Arabic evaluations mainly target downstream tasks and do not directly test controlled morphological generation from explicit lexical and feature-based input. We introduce YallaMorph, a large-scale benchmark for Arabic morphological generation covering verbs, nouns, adjectives, their cliticized forms, and invalid configurations. We evaluate multilingual and Arabic-oriented LLMs under diacritized and undiacritized settings over 600K benchmark entries. Results show that Arabic morphological generation remains difficult, especially for cliticized, unseen, and morphologically rare forms.

Anthology ID:: 2026.findings-emnlp.2035
Volume:: Findings of the Association for Computational Linguistics: EMNLP 2026
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Hung-Yi Lee, Sunipa Dev, Jessy Li, Desmond Elliott
Venue:: Findings
SIG:: SIGDAT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 43299–43315
Language:
URL:: https://aclanthology.org/2026.findings-emnlp.2035/
DOI:: 10.18653/2026.findings-emnlp.2035
Bibkey:
Cite (ACL):: Mahmoud Reda, Salam Khalifa, Reham Marzouk, and Nizar Habash. 2026. YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 43299–43315, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models (Reda et al., Findings 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.findings-emnlp.2035.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{reda-etal-2026-yallamorph,
    title = "{Y}alla{M}orph: A Benchmark for Evaluating {A}rabic Morphological Generation in Large Language Models",
    author = "Reda, Mahmoud  and
      Khalifa, Salam  and
      Marzouk, Reham  and
      Habash, Nizar",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.2035/",
    doi = "10.18653/2026.findings-emnlp.2035",
    pages = "43299--43315",
    ISBN = "979-8-89176-462-0",
    abstract = "Arabic morphology remains challenging for large language models, since fluent generation does not guarantee accurate morphosyntactic control. Existing Arabic evaluations mainly target downstream tasks and do not directly test controlled morphological generation from explicit lexical and feature-based input. We introduce YallaMorph, a large-scale benchmark for Arabic morphological generation covering verbs, nouns, adjectives, their cliticized forms, and invalid configurations. We evaluate multilingual and Arabic-oriented LLMs under diacritized and undiacritized settings over 600K benchmark entries. Results show that Arabic morphological generation remains difficult, especially for cliticized, unseen, and morphologically rare forms."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reda-etal-2026-yallamorph">
    <titleInfo>
        <title>YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mahmoud</namePart>
        <namePart type="family">Reda</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Salam</namePart>
        <namePart type="family">Khalifa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Reham</namePart>
        <namePart type="family">Marzouk</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nizar</namePart>
        <namePart type="family">Habash</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>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Arabic morphology remains challenging for large language models, since fluent generation does not guarantee accurate morphosyntactic control. Existing Arabic evaluations mainly target downstream tasks and do not directly test controlled morphological generation from explicit lexical and feature-based input. We introduce YallaMorph, a large-scale benchmark for Arabic morphological generation covering verbs, nouns, adjectives, their cliticized forms, and invalid configurations. We evaluate multilingual and Arabic-oriented LLMs under diacritized and undiacritized settings over 600K benchmark entries. Results show that Arabic morphological generation remains difficult, especially for cliticized, unseen, and morphologically rare forms.</abstract>
    <identifier type="citekey">reda-etal-2026-yallamorph</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.2035</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.2035/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>43299</start>
            <end>43315</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models
%A Reda, Mahmoud
%A Khalifa, Salam
%A Marzouk, Reham
%A Habash, Nizar
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F reda-etal-2026-yallamorph
%X Arabic morphology remains challenging for large language models, since fluent generation does not guarantee accurate morphosyntactic control. Existing Arabic evaluations mainly target downstream tasks and do not directly test controlled morphological generation from explicit lexical and feature-based input. We introduce YallaMorph, a large-scale benchmark for Arabic morphological generation covering verbs, nouns, adjectives, their cliticized forms, and invalid configurations. We evaluate multilingual and Arabic-oriented LLMs under diacritized and undiacritized settings over 600K benchmark entries. Results show that Arabic morphological generation remains difficult, especially for cliticized, unseen, and morphologically rare forms.
%R 10.18653/2026.findings-emnlp.2035
%U https://aclanthology.org/2026.findings-emnlp.2035/
%U https://doi.org/10.18653/2026.findings-emnlp.2035
%P 43299-43315

Download as File

Markdown (Informal)

[YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models](https://aclanthology.org/2026.findings-emnlp.2035/) (Reda et al., Findings 2026)

YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models (Reda et al., Findings 2026)

ACL

Mahmoud Reda, Salam Khalifa, Reham Marzouk, and Nizar Habash. 2026. YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 43299–43315, Budapest, Hungary. Association for Computational Linguistics.