Large Vocabulary Size Improves Large Language Models

Sho Takase; Ryokan Ri; Shun Kiyono; Takuya Kato

doi:10.18653/v1/2025.findings-acl.57

Large Vocabulary Size Improves Large Language Models

Sho Takase, Ryokan Ri, Shun Kiyono, Takuya Kato

Correct Metadata for

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>.

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

This paper empirically investigates the relationship between subword vocabulary size and the performance of large language models (LLMs) to provide insights on how to define the vocabulary size. Experimental results show that larger vocabulary sizes lead to better performance in LLMs. Moreover, we consider a continual training scenario where a pre-trained language model is trained on a different target language. We introduce a simple method to use a new vocabulary instead of the pre-defined one. We show that using the new vocabulary outperforms the model with the vocabulary used in pre-training.

Anthology ID:: 2025.findings-acl.57
Volume:: Findings of the Association for Computational Linguistics: ACL 2025
Month:: July
Year:: 2025
Address:: Vienna, Austria
Editors:: Wanxiang Che, Joyce Nabende, Ekaterina Shutova, Mohammad Taher Pilehvar
Venue:: Findings
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 1015–1026
Language:
URL:: https://aclanthology.org/2025.findings-acl.57/
DOI:: 10.18653/v1/2025.findings-acl.57
Bibkey:
Cite (ACL):: Sho Takase, Ryokan Ri, Shun Kiyono, and Takuya Kato. 2025. Large Vocabulary Size Improves Large Language Models. In Findings of the Association for Computational Linguistics: ACL 2025, pages 1015–1026, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):: Large Vocabulary Size Improves Large Language Models (Takase et al., Findings 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.findings-acl.57.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{takase-etal-2025-large,
    title = "Large Vocabulary Size Improves Large Language Models",
    author = "Takase, Sho  and
      Ri, Ryokan  and
      Kiyono, Shun  and
      Kato, Takuya",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-acl.57/",
    doi = "10.18653/v1/2025.findings-acl.57",
    pages = "1015--1026",
    ISBN = "979-8-89176-256-5",
    abstract = "This paper empirically investigates the relationship between subword vocabulary size and the performance of large language models (LLMs) to provide insights on how to define the vocabulary size. Experimental results show that larger vocabulary sizes lead to better performance in LLMs. Moreover, we consider a continual training scenario where a pre-trained language model is trained on a different target language. We introduce a simple method to use a new vocabulary instead of the pre-defined one. We show that using the new vocabulary outperforms the model with the vocabulary used in pre-training."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="takase-etal-2025-large">
    <titleInfo>
        <title>Large Vocabulary Size Improves Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sho</namePart>
        <namePart type="family">Takase</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ryokan</namePart>
        <namePart type="family">Ri</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shun</namePart>
        <namePart type="family">Kiyono</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Takuya</namePart>
        <namePart type="family">Kato</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>This paper empirically investigates the relationship between subword vocabulary size and the performance of large language models (LLMs) to provide insights on how to define the vocabulary size. Experimental results show that larger vocabulary sizes lead to better performance in LLMs. Moreover, we consider a continual training scenario where a pre-trained language model is trained on a different target language. We introduce a simple method to use a new vocabulary instead of the pre-defined one. We show that using the new vocabulary outperforms the model with the vocabulary used in pre-training.</abstract>
    <identifier type="citekey">takase-etal-2025-large</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.57</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.57/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>1015</start>
            <end>1026</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Large Vocabulary Size Improves Large Language Models
%A Takase, Sho
%A Ri, Ryokan
%A Kiyono, Shun
%A Kato, Takuya
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F takase-etal-2025-large
%X This paper empirically investigates the relationship between subword vocabulary size and the performance of large language models (LLMs) to provide insights on how to define the vocabulary size. Experimental results show that larger vocabulary sizes lead to better performance in LLMs. Moreover, we consider a continual training scenario where a pre-trained language model is trained on a different target language. We introduce a simple method to use a new vocabulary instead of the pre-defined one. We show that using the new vocabulary outperforms the model with the vocabulary used in pre-training.
%R 10.18653/v1/2025.findings-acl.57
%U https://aclanthology.org/2025.findings-acl.57/
%U https://doi.org/10.18653/v1/2025.findings-acl.57
%P 1015-1026

Download as File

Markdown (Informal)

[Large Vocabulary Size Improves Large Language Models](https://aclanthology.org/2025.findings-acl.57/) (Takase et al., Findings 2025)

Large Vocabulary Size Improves Large Language Models (Takase et al., Findings 2025)

ACL

Sho Takase, Ryokan Ri, Shun Kiyono, and Takuya Kato. 2025. Large Vocabulary Size Improves Large Language Models. In Findings of the Association for Computational Linguistics: ACL 2025, pages 1015–1026, Vienna, Austria. Association for Computational Linguistics.