UvA-MT’s Participation in the WMT26 General Translation Shared Task

Di Wu; Sergey Troshin; Wafaa Mohammed; Seth Aycock; Evgeniia Tokarchuk; Vlad Niculae; Christof Monz

UvA-MT’s Participation in the WMT26 General Translation Shared Task

Di Wu, Sergey Troshin, Wafaa Mohammed, Seth Aycock, Evgeniia Tokarchuk, Vlad Niculae, Christof Monz

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

This paper presents UvA-MT’s submission to the WMT 2026 General Machine Translation shared task, competing in the unconstrained track across all 23 translation directions. This year, we fully leverage the test-time methods of Large Language Models (LLMs) for machine translation. Specifically, (1) we use sequential sampling with a refinement prompt to generate a pool of translation candidates for each source sentence, a strategy shown to outperform traditional parallel sampling; and (2) we employ LLMs as pairwise judges to select the best candidates via a round-robin voting mechanism, with offline evaluation on the WMT25 benchmark showing a very clear improvement over point-wise best-of-N selection. Lastly, we simply apply these two strategies for the submission of WMT26.

Anthology ID:: 2026.wmt-main.82
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:: 1440–1446
Language:
URL:: https://aclanthology.org/2026.wmt-main.82/
DOI:
Bibkey:
Cite (ACL):: Di Wu, Sergey Troshin, Wafaa Mohammed, Seth Aycock, Evgeniia Tokarchuk, Vlad Niculae, and Christof Monz. 2026. UvA-MT’s Participation in the WMT26 General Translation Shared Task. In Proceedings of the Eleventh Conference on Machine Translation, pages 1440–1446, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: UvA-MT’s Participation in the WMT26 General Translation Shared Task (Wu et al., WMT 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.wmt-main.82.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{wu-etal-2026-uva,
    title = "{U}v{A}-{MT}{'}s Participation in the {WMT}26 General Translation Shared Task",
    author = "Wu, Di  and
      Troshin, Sergey  and
      Mohammed, Wafaa  and
      Aycock, Seth  and
      Tokarchuk, Evgeniia  and
      Niculae, Vlad  and
      Monz, Christof",
    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.82/",
    pages = "1440--1446",
    ISBN = "979-8-89176-474-3",
    abstract = "This paper presents UvA-MT{'}s submission to the WMT 2026 General Machine Translation shared task, competing in the unconstrained track across all 23 translation directions. This year, we fully leverage the test-time methods of Large Language Models (LLMs) for machine translation. Specifically, (1) we use sequential sampling with a refinement prompt to generate a pool of translation candidates for each source sentence, a strategy shown to outperform traditional parallel sampling; and (2) we employ LLMs as pairwise judges to select the best candidates via a round-robin voting mechanism, with offline evaluation on the WMT25 benchmark showing a very clear improvement over point-wise best-of-N selection. Lastly, we simply apply these two strategies for the submission of WMT26."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2026-uva">
    <titleInfo>
        <title>UvA-MT’s Participation in the WMT26 General Translation Shared Task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Di</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sergey</namePart>
        <namePart type="family">Troshin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wafaa</namePart>
        <namePart type="family">Mohammed</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seth</namePart>
        <namePart type="family">Aycock</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Evgeniia</namePart>
        <namePart type="family">Tokarchuk</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vlad</namePart>
        <namePart type="family">Niculae</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Christof</namePart>
        <namePart type="family">Monz</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>This paper presents UvA-MT’s submission to the WMT 2026 General Machine Translation shared task, competing in the unconstrained track across all 23 translation directions. This year, we fully leverage the test-time methods of Large Language Models (LLMs) for machine translation. Specifically, (1) we use sequential sampling with a refinement prompt to generate a pool of translation candidates for each source sentence, a strategy shown to outperform traditional parallel sampling; and (2) we employ LLMs as pairwise judges to select the best candidates via a round-robin voting mechanism, with offline evaluation on the WMT25 benchmark showing a very clear improvement over point-wise best-of-N selection. Lastly, we simply apply these two strategies for the submission of WMT26.</abstract>
    <identifier type="citekey">wu-etal-2026-uva</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.82/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1440</start>
            <end>1446</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T UvA-MT’s Participation in the WMT26 General Translation Shared Task
%A Wu, Di
%A Troshin, Sergey
%A Mohammed, Wafaa
%A Aycock, Seth
%A Tokarchuk, Evgeniia
%A Niculae, Vlad
%A Monz, Christof
%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 wu-etal-2026-uva
%X This paper presents UvA-MT’s submission to the WMT 2026 General Machine Translation shared task, competing in the unconstrained track across all 23 translation directions. This year, we fully leverage the test-time methods of Large Language Models (LLMs) for machine translation. Specifically, (1) we use sequential sampling with a refinement prompt to generate a pool of translation candidates for each source sentence, a strategy shown to outperform traditional parallel sampling; and (2) we employ LLMs as pairwise judges to select the best candidates via a round-robin voting mechanism, with offline evaluation on the WMT25 benchmark showing a very clear improvement over point-wise best-of-N selection. Lastly, we simply apply these two strategies for the submission of WMT26.
%U https://aclanthology.org/2026.wmt-main.82/
%P 1440-1446

Download as File

Markdown (Informal)

[UvA-MT’s Participation in the WMT26 General Translation Shared Task](https://aclanthology.org/2026.wmt-main.82/) (Wu et al., WMT 2026)

UvA-MT’s Participation in the WMT26 General Translation Shared Task (Wu et al., WMT 2026)

ACL

Di Wu, Sergey Troshin, Wafaa Mohammed, Seth Aycock, Evgeniia Tokarchuk, Vlad Niculae, and Christof Monz. 2026. UvA-MT’s Participation in the WMT26 General Translation Shared Task. In Proceedings of the Eleventh Conference on Machine Translation, pages 1440–1446, Budapest, Hungary. Association for Computational Linguistics.