SentinelQA: Task-Level Routing and Output Verification for Multilingual Instruction Following

Asher Egerton-Idehen

SentinelQA: Task-Level Routing and Output Verification for Multilingual Instruction Following

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 submission presents Team Sentinel’s approach to the WMT26 MIST shared task on multilingual instruction following. Built on Gemma-3-4B-IT, the system allocates its parameter budget across base and fine-tuned models, using a fixed task-level lookup to select between them. A verification layer checks output language, length constraints, repetition, and chat-template artefacts, with retries and repairs to improve output compliance.

Anthology ID:: 2026.wmt-main.127
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:: 1917–1924
Language:
URL:: https://aclanthology.org/2026.wmt-main.127/
DOI:
Bibkey:
Cite (ACL):: Asher Egerton-Idehen. 2026. SentinelQA: Task-Level Routing and Output Verification for Multilingual Instruction Following. In Proceedings of the Eleventh Conference on Machine Translation, pages 1917–1924, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: SentinelQA: Task-Level Routing and Output Verification for Multilingual Instruction Following (Egerton-Idehen, WMT 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.wmt-main.127.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{egerton-idehen-2026-sentinelqa,
    title = "{S}entinel{QA}: Task-Level Routing and Output Verification for Multilingual Instruction Following",
    author = "Egerton-Idehen, Asher",
    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.127/",
    pages = "1917--1924",
    ISBN = "979-8-89176-474-3",
    abstract = "This submission presents Team Sentinel{'}s approach to the WMT26 MIST shared task on multilingual instruction following. Built on Gemma-3-4B-IT, the system allocates its parameter budget across base and fine-tuned models, using a fixed task-level lookup to select between them. A verification layer checks output language, length constraints, repetition, and chat-template artefacts, with retries and repairs to improve output compliance."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="egerton-idehen-2026-sentinelqa">
    <titleInfo>
        <title>SentinelQA: Task-Level Routing and Output Verification for Multilingual Instruction Following</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Asher</namePart>
        <namePart type="family">Egerton-Idehen</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 submission presents Team Sentinel’s approach to the WMT26 MIST shared task on multilingual instruction following. Built on Gemma-3-4B-IT, the system allocates its parameter budget across base and fine-tuned models, using a fixed task-level lookup to select between them. A verification layer checks output language, length constraints, repetition, and chat-template artefacts, with retries and repairs to improve output compliance.</abstract>
    <identifier type="citekey">egerton-idehen-2026-sentinelqa</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.127/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1917</start>
            <end>1924</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T SentinelQA: Task-Level Routing and Output Verification for Multilingual Instruction Following
%A Egerton-Idehen, Asher
%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 egerton-idehen-2026-sentinelqa
%X This submission presents Team Sentinel’s approach to the WMT26 MIST shared task on multilingual instruction following. Built on Gemma-3-4B-IT, the system allocates its parameter budget across base and fine-tuned models, using a fixed task-level lookup to select between them. A verification layer checks output language, length constraints, repetition, and chat-template artefacts, with retries and repairs to improve output compliance.
%U https://aclanthology.org/2026.wmt-main.127/
%P 1917-1924

Download as File

Markdown (Informal)

[SentinelQA: Task-Level Routing and Output Verification for Multilingual Instruction Following](https://aclanthology.org/2026.wmt-main.127/) (Egerton-Idehen, WMT 2026)

SentinelQA: Task-Level Routing and Output Verification for Multilingual Instruction Following (Egerton-Idehen, WMT 2026)

ACL

Asher Egerton-Idehen. 2026. SentinelQA: Task-Level Routing and Output Verification for Multilingual Instruction Following. In Proceedings of the Eleventh Conference on Machine Translation, pages 1917–1924, Budapest, Hungary. Association for Computational Linguistics.