<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sant-etal-2026-task">
    <titleInfo>
        <title>Task-Preserving Multilingual Instruction Tuning for Open-Ended QA at WMT 2026 MIST</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Aleix</namePart>
        <namePart type="family">Sant</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jordi</namePart>
        <namePart type="family">Luque Serrano</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Carlos</namePart>
        <namePart type="family">Escolano Peinado</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 submission to the WMT 2026 Multilingual Instruction Shared Task. We adapt Qwen3-8B with LoRA using organiser-provided data, EuroAlpaca, a multilingual instruction dataset created through task-preserving localisation, and CrossEuroAlpaca, a cross-lingual augmentation that assigns different source and target languages to instructions, contexts and responses. Our system targets open-ended question answering (QA-OEG) in ten shared-task languages represented in the auxiliary data. Under matched decoding, adaptation improves the mean automatic Gemma-4 judge score on target-language QA-OEG by 7.8% relative to the base model. On the 27-language Aya Evaluation Suite, it yields relative gains of 41.5% in macro-averaged ROUGE-L and 2.9% in BERTScore-F1, with larger improvements in the target languages. However, these gains are task- and language-specific. Gemma-4 scores improve for QA-OEG and summarisation in the target languages but decline for context-grounded QA within this set and across all three tasks outside it.</abstract>
    <identifier type="citekey">sant-etal-2026-task</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.132/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1965</start>
            <end>1972</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Task-Preserving Multilingual Instruction Tuning for Open-Ended QA at WMT 2026 MIST
%A Sant, Aleix
%A Luque Serrano, Jordi
%A Escolano Peinado, Carlos
%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 sant-etal-2026-task
%X We describe our submission to the WMT 2026 Multilingual Instruction Shared Task. We adapt Qwen3-8B with LoRA using organiser-provided data, EuroAlpaca, a multilingual instruction dataset created through task-preserving localisation, and CrossEuroAlpaca, a cross-lingual augmentation that assigns different source and target languages to instructions, contexts and responses. Our system targets open-ended question answering (QA-OEG) in ten shared-task languages represented in the auxiliary data. Under matched decoding, adaptation improves the mean automatic Gemma-4 judge score on target-language QA-OEG by 7.8% relative to the base model. On the 27-language Aya Evaluation Suite, it yields relative gains of 41.5% in macro-averaged ROUGE-L and 2.9% in BERTScore-F1, with larger improvements in the target languages. However, these gains are task- and language-specific. Gemma-4 scores improve for QA-OEG and summarisation in the target languages but decline for context-grounded QA within this set and across all three tasks outside it.
%U https://aclanthology.org/2026.wmt-main.132/
%P 1965-1972

Markdown (Informal)

[Task-Preserving Multilingual Instruction Tuning for Open-Ended QA at WMT 2026 MIST](https://aclanthology.org/2026.wmt-main.132/) (Sant et al., WMT 2026)

• Task-Preserving Multilingual Instruction Tuning for Open-Ended QA at WMT 2026 MIST (Sant et al., WMT 2026)

ACL

• Aleix Sant, Jordi Luque Serrano, and Carlos Escolano Peinado. 2026. Task-Preserving Multilingual Instruction Tuning for Open-Ended QA at WMT 2026 MIST. In Proceedings of the Eleventh Conference on Machine Translation, pages 1965–1972, Budapest, Hungary. Association for Computational Linguistics.