Toward LLMs Beyond English-Centric Development

Sho Takase; Ukyo Honda

Toward LLMs Beyond English-Centric Development

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

Through an analysis of sequences generated by open-weight large language models (LLMs), we demonstrate that LLMs are heavily biased toward English. While continual pre-training is commonly used to adapt LLMs to a target language, we show that it does not offer a cost advantage over training from scratch, even for improving cultural understanding in the target language. These findings suggest that dedicated per-language investment may become increasingly important for future LLM development, rather than relying primarily on the expansion of English-centric resources.

Anthology ID:: 2026.aacl-short.53
Volume:: Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:: November
Year:: 2026
Address:: Hengqin, China
Editors:: Yue Zhang, Ruifeng Xu, Ayu Purwarianti, Tong Rong, Jun Suzuki
Venues:: AACL | IJCNLP
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 830–840
Language:
URL:: https://aclanthology.org/2026.aacl-short.53/
DOI:
Bibkey:
Cite (ACL):: Sho Takase and Ukyo Honda. 2026. Toward LLMs Beyond English-Centric Development. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 830–840, Hengqin, China. Association for Computational Linguistics.
Cite (Informal):: Toward LLMs Beyond English-Centric Development (Takase & Honda, AACL-IJCNLP 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.aacl-short.53.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{takase-honda-2026-toward,
    title = "Toward {LLM}s Beyond {E}nglish-Centric Development",
    author = "Takase, Sho  and
      Honda, Ukyo",
    editor = "Zhang, Yue  and
      Xu, Ruifeng  and
      Purwarianti, Ayu  and
      Rong, Tong  and
      Suzuki, Jun",
    booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 2: Short Papers)",
    month = nov,
    year = "2026",
    address = "Hengqin, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.aacl-short.53/",
    pages = "830--840",
    ISBN = "979-8-89176-440-8",
    abstract = "Through an analysis of sequences generated by open-weight large language models (LLMs), we demonstrate that LLMs are heavily biased toward English. While continual pre-training is commonly used to adapt LLMs to a target language, we show that it does not offer a cost advantage over training from scratch, even for improving cultural understanding in the target language. These findings suggest that dedicated per-language investment may become increasingly important for future LLM development, rather than relying primarily on the expansion of English-centric resources."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="takase-honda-2026-toward">
    <titleInfo>
        <title>Toward LLMs Beyond English-Centric Development</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">Ukyo</namePart>
        <namePart type="family">Honda</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruifeng</namePart>
            <namePart type="family">Xu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ayu</namePart>
            <namePart type="family">Purwarianti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tong</namePart>
            <namePart type="family">Rong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun</namePart>
            <namePart type="family">Suzuki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hengqin, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-440-8</identifier>
    </relatedItem>
    <abstract>Through an analysis of sequences generated by open-weight large language models (LLMs), we demonstrate that LLMs are heavily biased toward English. While continual pre-training is commonly used to adapt LLMs to a target language, we show that it does not offer a cost advantage over training from scratch, even for improving cultural understanding in the target language. These findings suggest that dedicated per-language investment may become increasingly important for future LLM development, rather than relying primarily on the expansion of English-centric resources.</abstract>
    <identifier type="citekey">takase-honda-2026-toward</identifier>
    <location>
        <url>https://aclanthology.org/2026.aacl-short.53/</url>
    </location>
    <part>
        <date>2026-11</date>
        <extent unit="page">
            <start>830</start>
            <end>840</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Toward LLMs Beyond English-Centric Development
%A Takase, Sho
%A Honda, Ukyo
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-440-8
%F takase-honda-2026-toward
%X Through an analysis of sequences generated by open-weight large language models (LLMs), we demonstrate that LLMs are heavily biased toward English. While continual pre-training is commonly used to adapt LLMs to a target language, we show that it does not offer a cost advantage over training from scratch, even for improving cultural understanding in the target language. These findings suggest that dedicated per-language investment may become increasingly important for future LLM development, rather than relying primarily on the expansion of English-centric resources.
%U https://aclanthology.org/2026.aacl-short.53/
%P 830-840

Download as File

Markdown (Informal)

[Toward LLMs Beyond English-Centric Development](https://aclanthology.org/2026.aacl-short.53/) (Takase & Honda, AACL-IJCNLP 2026)

Toward LLMs Beyond English-Centric Development (Takase & Honda, AACL-IJCNLP 2026)

ACL

Sho Takase and Ukyo Honda. 2026. Toward LLMs Beyond English-Centric Development. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 830–840, Hengqin, China. Association for Computational Linguistics.