A* Decoding for Machine Translation in LLMs - SRPOL Participation in WMT2025

Adam Dobrowolski; Paweł Przewłocki; Paweł Przybysz; Marcin Szymański; Dawid Siwicki

doi:10.18653/v1/2025.wmt-1.42

A* Decoding for Machine Translation in LLMs - SRPOL Participation in WMT2025

Adam Dobrowolski, Paweł Przewłocki, Paweł Przybysz, Marcin Szymański, Dawid Siwicki

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 <b>...</b> for bold, <i>...</i> for italic, and <url>...</url> for URLs.

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

SRPOL team submission to WMT2025 introduces innovative approach using A* (A-star) algorithm of decoding in EuroLLM which gives diverse set of translation hypotheses. Subsequent reranking by Comet-QE and NLLB chooses the best of the diversed hypotheses which gives significant improvement of translation quality. The A* algorithm can be applied to decoding in any LLMs or other translation models. The experiment shows that by using free, openly accessible MT models you can achieve translation quality of the best online translators and LLMs using just a PC under your desk.

Anthology ID:: 2025.wmt-1.42
Volume:: Proceedings of the Tenth Conference on Machine Translation
Month:: November
Year:: 2025
Address:: Suzhou, China
Editors:: Barry Haddow, Tom Kocmi, Philipp Koehn, Christof Monz
Venue:: WMT
SIG:: SIGMT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 666–670
Language:
URL:: https://aclanthology.org/2025.wmt-1.42/
DOI:: 10.18653/v1/2025.wmt-1.42
Bibkey:
Cite (ACL):: Adam Dobrowolski, Paweł Przewłocki, Paweł Przybysz, Marcin Szymański, and Dawid Siwicki. 2025. A* Decoding for Machine Translation in LLMs - SRPOL Participation in WMT2025. In Proceedings of the Tenth Conference on Machine Translation, pages 666–670, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):: A* Decoding for Machine Translation in LLMs - SRPOL Participation in WMT2025 (Dobrowolski et al., WMT 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.wmt-1.42.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{dobrowolski-etal-2025-decoding,
    title = "A* Decoding for Machine Translation in {LLM}s - {SRPOL} Participation in {WMT}2025",
    author = "Dobrowolski, Adam  and
      Przew{\l}ocki, Pawe{\l}  and
      Przybysz, Pawe{\l}  and
      Szyma{\'n}ski, Marcin  and
      Siwicki, Dawid",
    editor = "Haddow, Barry  and
      Kocmi, Tom  and
      Koehn, Philipp  and
      Monz, Christof",
    booktitle = "Proceedings of the Tenth Conference on Machine Translation",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.wmt-1.42/",
    doi = "10.18653/v1/2025.wmt-1.42",
    pages = "666--670",
    ISBN = "979-8-89176-341-8",
    abstract = "SRPOL team submission to WMT2025 introduces innovative approach using A* (A-star) algorithm of decoding in EuroLLM which gives diverse set of translation hypotheses. Subsequent reranking by Comet-QE and NLLB chooses the best of the diversed hypotheses which gives significant improvement of translation quality. The A* algorithm can be applied to decoding in any LLMs or other translation models. The experiment shows that by using free, openly accessible MT models you can achieve translation quality of the best online translators and LLMs using just a PC under your desk."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dobrowolski-etal-2025-decoding">
    <titleInfo>
        <title>A* Decoding for Machine Translation in LLMs - SRPOL Participation in WMT2025</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Adam</namePart>
        <namePart type="family">Dobrowolski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Paweł</namePart>
        <namePart type="family">Przewłocki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Paweł</namePart>
        <namePart type="family">Przybysz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marcin</namePart>
        <namePart type="family">Szymański</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dawid</namePart>
        <namePart type="family">Siwicki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Tenth 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">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-341-8</identifier>
    </relatedItem>
    <abstract>SRPOL team submission to WMT2025 introduces innovative approach using A* (A-star) algorithm of decoding in EuroLLM which gives diverse set of translation hypotheses. Subsequent reranking by Comet-QE and NLLB chooses the best of the diversed hypotheses which gives significant improvement of translation quality. The A* algorithm can be applied to decoding in any LLMs or other translation models. The experiment shows that by using free, openly accessible MT models you can achieve translation quality of the best online translators and LLMs using just a PC under your desk.</abstract>
    <identifier type="citekey">dobrowolski-etal-2025-decoding</identifier>
    <identifier type="doi">10.18653/v1/2025.wmt-1.42</identifier>
    <location>
        <url>https://aclanthology.org/2025.wmt-1.42/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>666</start>
            <end>670</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T A* Decoding for Machine Translation in LLMs - SRPOL Participation in WMT2025
%A Dobrowolski, Adam
%A Przewłocki, Paweł
%A Przybysz, Paweł
%A Szymański, Marcin
%A Siwicki, Dawid
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Tenth Conference on Machine Translation
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-341-8
%F dobrowolski-etal-2025-decoding
%X SRPOL team submission to WMT2025 introduces innovative approach using A* (A-star) algorithm of decoding in EuroLLM which gives diverse set of translation hypotheses. Subsequent reranking by Comet-QE and NLLB chooses the best of the diversed hypotheses which gives significant improvement of translation quality. The A* algorithm can be applied to decoding in any LLMs or other translation models. The experiment shows that by using free, openly accessible MT models you can achieve translation quality of the best online translators and LLMs using just a PC under your desk.
%R 10.18653/v1/2025.wmt-1.42
%U https://aclanthology.org/2025.wmt-1.42/
%U https://doi.org/10.18653/v1/2025.wmt-1.42
%P 666-670

Download as File

Markdown (Informal)

[A* Decoding for Machine Translation in LLMs - SRPOL Participation in WMT2025](https://aclanthology.org/2025.wmt-1.42/) (Dobrowolski et al., WMT 2025)

A* Decoding for Machine Translation in LLMs - SRPOL Participation in WMT2025 (Dobrowolski et al., WMT 2025)

ACL

Adam Dobrowolski, Paweł Przewłocki, Paweł Przybysz, Marcin Szymański, and Dawid Siwicki. 2025. A* Decoding for Machine Translation in LLMs - SRPOL Participation in WMT2025. In Proceedings of the Tenth Conference on Machine Translation, pages 666–670, Suzhou, China. Association for Computational Linguistics.