@inproceedings{alakeel-etal-2026-morphemes,
title = "Morphemes without Borders: Evaluating Root{--}Pattern Morphology in {A}rabic Tokenizers and {LLM}s",
author = "Alakeel, Yara Yousif and
Qwaider, Chatrine and
Aldarmaki, Hanan and
Alqahtani, Sawsan",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.923/",
doi = "10.63317/3bk9j7feheoq",
pages = "11787--11799",
abstract = "This work investigates how effectively large language models (LLMs) and their tokenization schemes represent and generate Arabic root{--}pattern morphology, probing whether they capture genuine morphological structure or rely on surface memorization. Arabic morphological system provides a rich testbed for analyzing how LLMs handle complex, non-concatenative forms and how tokenization choices influence this process. Our study begins with an evaluation of morphological fidelity across Arabic and multilingual tokenizers against gold-standard segmentation, followed by an analysis of LLM performance in productive root{--}pattern generation using a newly developed benchmark. Our findings across seven Arabic-centric and multilingual LLMs and their respective tokenizers reveal that tokenizer morphological alignment is not necessary nor sufficient for morphological generation, which questions the role of morphological tokenization in downstream performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alakeel-etal-2026-morphemes">
<titleInfo>
<title>Morphemes without Borders: Evaluating Root–Pattern Morphology in Arabic Tokenizers and LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yara</namePart>
<namePart type="given">Yousif</namePart>
<namePart type="family">Alakeel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chatrine</namePart>
<namePart type="family">Qwaider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanan</namePart>
<namePart type="family">Aldarmaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sawsan</namePart>
<namePart type="family">Alqahtani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This work investigates how effectively large language models (LLMs) and their tokenization schemes represent and generate Arabic root–pattern morphology, probing whether they capture genuine morphological structure or rely on surface memorization. Arabic morphological system provides a rich testbed for analyzing how LLMs handle complex, non-concatenative forms and how tokenization choices influence this process. Our study begins with an evaluation of morphological fidelity across Arabic and multilingual tokenizers against gold-standard segmentation, followed by an analysis of LLM performance in productive root–pattern generation using a newly developed benchmark. Our findings across seven Arabic-centric and multilingual LLMs and their respective tokenizers reveal that tokenizer morphological alignment is not necessary nor sufficient for morphological generation, which questions the role of morphological tokenization in downstream performance.</abstract>
<identifier type="citekey">alakeel-etal-2026-morphemes</identifier>
<identifier type="doi">10.63317/3bk9j7feheoq</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.923/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>11787</start>
<end>11799</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Morphemes without Borders: Evaluating Root–Pattern Morphology in Arabic Tokenizers and LLMs
%A Alakeel, Yara Yousif
%A Qwaider, Chatrine
%A Aldarmaki, Hanan
%A Alqahtani, Sawsan
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F alakeel-etal-2026-morphemes
%X This work investigates how effectively large language models (LLMs) and their tokenization schemes represent and generate Arabic root–pattern morphology, probing whether they capture genuine morphological structure or rely on surface memorization. Arabic morphological system provides a rich testbed for analyzing how LLMs handle complex, non-concatenative forms and how tokenization choices influence this process. Our study begins with an evaluation of morphological fidelity across Arabic and multilingual tokenizers against gold-standard segmentation, followed by an analysis of LLM performance in productive root–pattern generation using a newly developed benchmark. Our findings across seven Arabic-centric and multilingual LLMs and their respective tokenizers reveal that tokenizer morphological alignment is not necessary nor sufficient for morphological generation, which questions the role of morphological tokenization in downstream performance.
%R 10.63317/3bk9j7feheoq
%U https://aclanthology.org/2026.lrec-1.923/
%U https://doi.org/10.63317/3bk9j7feheoq
%P 11787-11799
Markdown (Informal)
[Morphemes without Borders: Evaluating Root–Pattern Morphology in Arabic Tokenizers and LLMs](https://aclanthology.org/2026.lrec-1.923/) (Alakeel et al., LREC 2026)
ACL