Are LLMs Good Text Diacritizers? An Arabic and Yoruba Case Study

Hawau Olamide Toyin; Samar Mohamed Magdy; Hanan Aldarmaki

doi:10.63317/5cm5exvnmd9r

Are LLMs Good Text Diacritizers? An Arabic and Yoruba Case Study

Hawau Olamide Toyin, Samar Mohamed Magdy, Hanan Aldarmaki

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 external publication .)

Authors concatenated from the text boxes above:

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

Abstract

We investigate the effectiveness of large language models (LLMs) for text diacritization in two typologically distinct languages: Arabic and Yoruba. To enable a rigorous evaluation, we introduce a novel multilingual dataset MultiDiac, with diverse samples that capture a range of diacritic ambiguities. We evaluate 12 LLMs varying in size, accessibility, and language coverage, and benchmark them against 4 specialized diacritization models. Additionally, we fine-tune four small open-source models using LoRA for Yoruba. Our results show that many off-the-shelf LLMs outperform specialized diacritization models for both Arabic and Yoruba, but smaller models suffer from hallucinations. We find that fine-tuning on a small dataset can help improve diacritization performance and reduce hallucination rates for Yoruba.

Anthology ID:: 2026.lrec-1.40
Volume:: Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:: May
Year:: 2026
Address:: Palma de Mallorca, Spain
Editors:: Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:: LREC
SIG:
Publisher:: ELRA Language Resource Association
Note:
Pages:: 580–589
Language:
External URL:: https://lrec.elra.info/lrec2026-main-040
DOI:: 10.63317/5cm5exvnmd9r
Bibkey:
Cite (ACL):: Hawau Olamide Toyin, Samar Mohamed Magdy, and Hanan Aldarmaki. 2026. Are LLMs Good Text Diacritizers? An Arabic and Yoruba Case Study. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 580–589, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):: Are LLMs Good Text Diacritizers? An Arabic and Yoruba Case Study (Toyin et al., LREC 2026)
Copy Citation:

External Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{toyin-etal-2026-llms,
    title = "Are {LLM}s Good Text Diacritizers? An {A}rabic and {Y}oruba Case Study",
    author = "Toyin, Hawau Olamide  and
      Magdy, Samar Mohamed  and
      Aldarmaki, Hanan",
    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-1.40/",
    doi = "10.63317/5cm5exvnmd9r",
    pages = "580--589",
    abstract = "We investigate the effectiveness of large language models (LLMs) for text diacritization in two typologically distinct languages: Arabic and Yoruba. To enable a rigorous evaluation, we introduce a novel multilingual dataset MultiDiac, with diverse samples that capture a range of diacritic ambiguities. We evaluate 12 LLMs varying in size, accessibility, and language coverage, and benchmark them against 4 specialized diacritization models. Additionally, we fine-tune four small open-source models using LoRA for Yoruba. Our results show that many off-the-shelf LLMs outperform specialized diacritization models for both Arabic and Yoruba, but smaller models suffer from hallucinations. We find that fine-tuning on a small dataset can help improve diacritization performance and reduce hallucination rates for Yoruba."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="toyin-etal-2026-llms">
    <titleInfo>
        <title>Are LLMs Good Text Diacritizers? An Arabic and Yoruba Case Study</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hawau</namePart>
        <namePart type="given">Olamide</namePart>
        <namePart type="family">Toyin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Samar</namePart>
        <namePart type="given">Mohamed</namePart>
        <namePart type="family">Magdy</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>
    <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>We investigate the effectiveness of large language models (LLMs) for text diacritization in two typologically distinct languages: Arabic and Yoruba. To enable a rigorous evaluation, we introduce a novel multilingual dataset MultiDiac, with diverse samples that capture a range of diacritic ambiguities. We evaluate 12 LLMs varying in size, accessibility, and language coverage, and benchmark them against 4 specialized diacritization models. Additionally, we fine-tune four small open-source models using LoRA for Yoruba. Our results show that many off-the-shelf LLMs outperform specialized diacritization models for both Arabic and Yoruba, but smaller models suffer from hallucinations. We find that fine-tuning on a small dataset can help improve diacritization performance and reduce hallucination rates for Yoruba.</abstract>
    <identifier type="citekey">toyin-etal-2026-llms</identifier>
    <identifier type="doi">10.63317/5cm5exvnmd9r</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.40/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>580</start>
            <end>589</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Are LLMs Good Text Diacritizers? An Arabic and Yoruba Case Study
%A Toyin, Hawau Olamide
%A Magdy, Samar Mohamed
%A Aldarmaki, Hanan
%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 toyin-etal-2026-llms
%X We investigate the effectiveness of large language models (LLMs) for text diacritization in two typologically distinct languages: Arabic and Yoruba. To enable a rigorous evaluation, we introduce a novel multilingual dataset MultiDiac, with diverse samples that capture a range of diacritic ambiguities. We evaluate 12 LLMs varying in size, accessibility, and language coverage, and benchmark them against 4 specialized diacritization models. Additionally, we fine-tune four small open-source models using LoRA for Yoruba. Our results show that many off-the-shelf LLMs outperform specialized diacritization models for both Arabic and Yoruba, but smaller models suffer from hallucinations. We find that fine-tuning on a small dataset can help improve diacritization performance and reduce hallucination rates for Yoruba.
%R 10.63317/5cm5exvnmd9r
%U https://aclanthology.org/2026.lrec-1.40/
%U https://doi.org/10.63317/5cm5exvnmd9r
%P 580-589

Download as File

Markdown (Informal)

[Are LLMs Good Text Diacritizers? An Arabic and Yoruba Case Study](https://aclanthology.org/2026.lrec-1.40/) (Toyin et al., LREC 2026)

Are LLMs Good Text Diacritizers? An Arabic and Yoruba Case Study (Toyin et al., LREC 2026)

ACL

Hawau Olamide Toyin, Samar Mohamed Magdy, and Hanan Aldarmaki. 2026. Are LLMs Good Text Diacritizers? An Arabic and Yoruba Case Study. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 580–589, Palma de Mallorca, Spain. ELRA Language Resource Association.