CUNI-MH and CUNI-EdUKate at the WMT26 General MT Shared Task

Miroslav Hrabal; Josef Jon; Ondřej Bojar

CUNI-MH and CUNI-EdUKate at the WMT26 General MT Shared Task

Miroslav Hrabal, Josef Jon, Ondřej Bojar

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 describe our constrained CUNI-MH-v3 (based on Qwen3-14B) and unconstrained CUNI-EdUKate (based on Granite 4.1 8B) submissions for the WMT26 General MT shared task. Both submissions use a three-stage training procedure: QLoRA supervised fine-tuning on synthetic sentence pairs, continued supervised fine-tuning on a smaller mixture of paragraph-level and instruction-oriented examples, and iterative preference optimization with automatically generated and scored preference pairs. We document the data construction, training setup, checkpoint selection, and evaluation. We also share the training data and model checkpoints for our constrained system.

Anthology ID:: 2026.wmt-main.67
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:: 1264–1270
Language:
URL:: https://aclanthology.org/2026.wmt-main.67/
DOI:
Bibkey:
Cite (ACL):: Miroslav Hrabal, Josef Jon, and Ondřej Bojar. 2026. CUNI-MH and CUNI-EdUKate at the WMT26 General MT Shared Task. In Proceedings of the Eleventh Conference on Machine Translation, pages 1264–1270, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: CUNI-MH and CUNI-EdUKate at the WMT26 General MT Shared Task (Hrabal et al., WMT 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.wmt-main.67.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{hrabal-etal-2026-cuni,
    title = "{CUNI}-{MH} and {CUNI}-{E}d{UK}ate at the {WMT}26 General {MT} Shared Task",
    author = "Hrabal, Miroslav  and
      Jon, Josef  and
      Bojar, Ond{\v{r}}ej",
    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.67/",
    pages = "1264--1270",
    ISBN = "979-8-89176-474-3",
    abstract = "We describe our constrained CUNI-MH-v3 (based on Qwen3-14B) and unconstrained CUNI-EdUKate (based on Granite 4.1 8B) submissions for the WMT26 General MT shared task. Both submissions use a three-stage training procedure: QLoRA supervised fine-tuning on synthetic sentence pairs, continued supervised fine-tuning on a smaller mixture of paragraph-level and instruction-oriented examples, and iterative preference optimization with automatically generated and scored preference pairs. We document the data construction, training setup, checkpoint selection, and evaluation. We also share the training data and model checkpoints for our constrained system."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hrabal-etal-2026-cuni">
    <titleInfo>
        <title>CUNI-MH and CUNI-EdUKate at the WMT26 General MT Shared Task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Miroslav</namePart>
        <namePart type="family">Hrabal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Josef</namePart>
        <namePart type="family">Jon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ondřej</namePart>
        <namePart type="family">Bojar</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 describe our constrained CUNI-MH-v3 (based on Qwen3-14B) and unconstrained CUNI-EdUKate (based on Granite 4.1 8B) submissions for the WMT26 General MT shared task. Both submissions use a three-stage training procedure: QLoRA supervised fine-tuning on synthetic sentence pairs, continued supervised fine-tuning on a smaller mixture of paragraph-level and instruction-oriented examples, and iterative preference optimization with automatically generated and scored preference pairs. We document the data construction, training setup, checkpoint selection, and evaluation. We also share the training data and model checkpoints for our constrained system.</abstract>
    <identifier type="citekey">hrabal-etal-2026-cuni</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.67/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1264</start>
            <end>1270</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T CUNI-MH and CUNI-EdUKate at the WMT26 General MT Shared Task
%A Hrabal, Miroslav
%A Jon, Josef
%A Bojar, Ondřej
%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 hrabal-etal-2026-cuni
%X We describe our constrained CUNI-MH-v3 (based on Qwen3-14B) and unconstrained CUNI-EdUKate (based on Granite 4.1 8B) submissions for the WMT26 General MT shared task. Both submissions use a three-stage training procedure: QLoRA supervised fine-tuning on synthetic sentence pairs, continued supervised fine-tuning on a smaller mixture of paragraph-level and instruction-oriented examples, and iterative preference optimization with automatically generated and scored preference pairs. We document the data construction, training setup, checkpoint selection, and evaluation. We also share the training data and model checkpoints for our constrained system.
%U https://aclanthology.org/2026.wmt-main.67/
%P 1264-1270

Download as File

Markdown (Informal)

[CUNI-MH and CUNI-EdUKate at the WMT26 General MT Shared Task](https://aclanthology.org/2026.wmt-main.67/) (Hrabal et al., WMT 2026)

CUNI-MH and CUNI-EdUKate at the WMT26 General MT Shared Task (Hrabal et al., WMT 2026)

ACL

Miroslav Hrabal, Josef Jon, and Ondřej Bojar. 2026. CUNI-MH and CUNI-EdUKate at the WMT26 General MT Shared Task. In Proceedings of the Eleventh Conference on Machine Translation, pages 1264–1270, Budapest, Hungary. Association for Computational Linguistics.