Zolint at WMT 2026: A Multitask LLM Submission for the Low-Resource Ukrainian Track

Lingchu Yang; Zitong Fu; Hämmerl Kathy; Masaki Ito

Zolint at WMT 2026: A Multitask LLM Submission for the Low-Resource Ukrainian Track

Lingchu Yang, Zitong Fu, Hämmerl Kathy, Masaki Ito

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

We present a unified multi-task fine-tuning system submitted to the WMT 2026 Shared Task on Multitask LLMs with Limited Resources (Ukrainian track), covering machine translation, spelling correction, grammar correction, question answering, and mathematical reasoning. Our system is built on Qwen3.5-2B-Instruct and adopts a two-stage training pipeline that gradually introduces heterogeneous tasks while replaying selected data from earlier stages to mitigate catastrophic forgetting. The resulting model achieves a strong balance across all evaluated tasks, consistently outperforming the official baseline and obtaining the best performance on every task except question answering. Our results demonstrate that staged multi-task fine-tuning is an effective strategy for adapting compact multilingual LLMs under limited-resource constraints.

Anthology ID:: 2026.wmt-main.213
Volume:: Proceedings of the Eleventh Conference on Machine Translation
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Barry Haddow, Tom Kocmi, Philipp Koehn, Christof Monz
Venues:: WMT | WS
SIG:: SIGMT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 2689–2696
Language:
URL:: https://aclanthology.org/2026.wmt-main.213/
DOI:
Bibkey:
Cite (ACL):: Lingchu Yang, Zitong Fu, Hämmerl Kathy, and Masaki Ito. 2026. Zolint at WMT 2026: A Multitask LLM Submission for the Low-Resource Ukrainian Track. In Proceedings of the Eleventh Conference on Machine Translation, pages 2689–2696, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Zolint at WMT 2026: A Multitask LLM Submission for the Low-Resource Ukrainian Track (Yang et al., WMT 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.wmt-main.213.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{yang-etal-2026-zolint,
    title = "Zolint at {WMT} 2026: A Multitask {LLM} Submission for the Low-Resource {U}krainian Track",
    author = {Yang, Lingchu  and
      Fu, Zitong  and
      Kathy, H{\"a}mmerl  and
      Ito, Masaki},
    editor = "Haddow, Barry  and
      Kocmi, Tom  and
      Koehn, Philipp  and
      Monz, Christof",
    booktitle = "Proceedings of the Eleventh Conference on Machine Translation",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.wmt-main.213/",
    pages = "2689--2696",
    ISBN = "979-8-89176-474-3",
    abstract = "We present a unified multi-task fine-tuning system submitted to the WMT 2026 Shared Task on Multitask LLMs with Limited Resources (Ukrainian track), covering machine translation, spelling correction, grammar correction, question answering, and mathematical reasoning. Our system is built on Qwen3.5-2B-Instruct and adopts a two-stage training pipeline that gradually introduces heterogeneous tasks while replaying selected data from earlier stages to mitigate catastrophic forgetting. The resulting model achieves a strong balance across all evaluated tasks, consistently outperforming the official baseline and obtaining the best performance on every task except question answering. Our results demonstrate that staged multi-task fine-tuning is an effective strategy for adapting compact multilingual LLMs under limited-resource constraints."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-zolint">
    <titleInfo>
        <title>Zolint at WMT 2026: A Multitask LLM Submission for the Low-Resource Ukrainian Track</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lingchu</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zitong</namePart>
        <namePart type="family">Fu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hämmerl</namePart>
        <namePart type="family">Kathy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Masaki</namePart>
        <namePart type="family">Ito</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>Proceedings of the Eleventh Conference on Machine Translation</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Barry</namePart>
            <namePart type="family">Haddow</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tom</namePart>
            <namePart type="family">Kocmi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Philipp</namePart>
            <namePart type="family">Koehn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christof</namePart>
            <namePart type="family">Monz</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">979-8-89176-474-3</identifier>
    </relatedItem>
    <abstract>We present a unified multi-task fine-tuning system submitted to the WMT 2026 Shared Task on Multitask LLMs with Limited Resources (Ukrainian track), covering machine translation, spelling correction, grammar correction, question answering, and mathematical reasoning. Our system is built on Qwen3.5-2B-Instruct and adopts a two-stage training pipeline that gradually introduces heterogeneous tasks while replaying selected data from earlier stages to mitigate catastrophic forgetting. The resulting model achieves a strong balance across all evaluated tasks, consistently outperforming the official baseline and obtaining the best performance on every task except question answering. Our results demonstrate that staged multi-task fine-tuning is an effective strategy for adapting compact multilingual LLMs under limited-resource constraints.</abstract>
    <identifier type="citekey">yang-etal-2026-zolint</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.213/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>2689</start>
            <end>2696</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Zolint at WMT 2026: A Multitask LLM Submission for the Low-Resource Ukrainian Track
%A Yang, Lingchu
%A Fu, Zitong
%A Kathy, Hämmerl
%A Ito, Masaki
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Eleventh Conference on Machine Translation
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-474-3
%F yang-etal-2026-zolint
%X We present a unified multi-task fine-tuning system submitted to the WMT 2026 Shared Task on Multitask LLMs with Limited Resources (Ukrainian track), covering machine translation, spelling correction, grammar correction, question answering, and mathematical reasoning. Our system is built on Qwen3.5-2B-Instruct and adopts a two-stage training pipeline that gradually introduces heterogeneous tasks while replaying selected data from earlier stages to mitigate catastrophic forgetting. The resulting model achieves a strong balance across all evaluated tasks, consistently outperforming the official baseline and obtaining the best performance on every task except question answering. Our results demonstrate that staged multi-task fine-tuning is an effective strategy for adapting compact multilingual LLMs under limited-resource constraints.
%U https://aclanthology.org/2026.wmt-main.213/
%P 2689-2696

Download as File

Markdown (Informal)

[Zolint at WMT 2026: A Multitask LLM Submission for the Low-Resource Ukrainian Track](https://aclanthology.org/2026.wmt-main.213/) (Yang et al., WMT 2026)

Zolint at WMT 2026: A Multitask LLM Submission for the Low-Resource Ukrainian Track (Yang et al., WMT 2026)

ACL

Lingchu Yang, Zitong Fu, Hämmerl Kathy, and Masaki Ito. 2026. Zolint at WMT 2026: A Multitask LLM Submission for the Low-Resource Ukrainian Track. In Proceedings of the Eleventh Conference on Machine Translation, pages 2689–2696, Budapest, Hungary. Association for Computational Linguistics.