Reasoning about In-Context Samples for Machine-Translation

Maxime Bouthors; Josep M. Crego; François Yvon

Reasoning about In-Context Samples for Machine-Translation

Maxime Bouthors, Josep Crego, François Yvon

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

Large Language Models (LLMs) can be trained to perform chain-of-thoughts reasoning in order to improve the reliability of their responses. In this work, we investigate how explicit reasoning can be leveraged for Machine Translation (MT). We introduce a novel fragment-based reasoning framework in which the model first extracts parallel source-target fragments from retrieved similar examples, and uses these fragments as intermediate reasoning traces to produce the final translation. To train our model, we distill silver fragments and drafts from a larger teacher model. Our experiments with the Qwen3 model family, over 6 languages, including up to 5 domains per language, demonstrates that fragment-based MT significantly outperforms alternative methods like standard k-shot, or drafting.

Anthology ID:: 2026.findings-emnlp.168
Volume:: Findings of the Association for Computational Linguistics: EMNLP 2026
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Hung-Yi Lee, Sunipa Dev, Jessy Li, Desmond Elliott
Venue:: Findings
SIG:: SIGDAT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 3546–3566
Language:
URL:: https://aclanthology.org/2026.findings-emnlp.168/
DOI:
Bibkey:
Cite (ACL):: Maxime Bouthors, Josep Crego, and François Yvon. 2026. Reasoning about In-Context Samples for Machine-Translation. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 3546–3566, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Reasoning about In-Context Samples for Machine-Translation (Bouthors et al., Findings 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.findings-emnlp.168.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{bouthors-etal-2026-reasoning,
    title = "Reasoning about In-Context Samples for Machine-Translation",
    author = "Bouthors, Maxime  and
      Crego, Josep  and
      Yvon, Fran{\c{c}}ois",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.168/",
    pages = "3546--3566",
    ISBN = "979-8-89176-462-0",
    abstract = "Large Language Models (LLMs) can be trained to perform chain-of-thoughts reasoning in order to improve the reliability of their responses. In this work, we investigate how explicit reasoning can be leveraged for Machine Translation (MT). We introduce a novel fragment-based reasoning framework in which the model first extracts parallel source-target fragments from retrieved similar examples, and uses these fragments as intermediate reasoning traces to produce the final translation. To train our model, we distill silver fragments and drafts from a larger teacher model. Our experiments with the Qwen3 model family, over 6 languages, including up to 5 domains per language, demonstrates that fragment-based MT significantly outperforms alternative methods like standard k-shot, or drafting."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bouthors-etal-2026-reasoning">
    <titleInfo>
        <title>Reasoning about In-Context Samples for Machine-Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Maxime</namePart>
        <namePart type="family">Bouthors</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Josep</namePart>
        <namePart type="family">Crego</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">François</namePart>
        <namePart type="family">Yvon</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>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Large Language Models (LLMs) can be trained to perform chain-of-thoughts reasoning in order to improve the reliability of their responses. In this work, we investigate how explicit reasoning can be leveraged for Machine Translation (MT). We introduce a novel fragment-based reasoning framework in which the model first extracts parallel source-target fragments from retrieved similar examples, and uses these fragments as intermediate reasoning traces to produce the final translation. To train our model, we distill silver fragments and drafts from a larger teacher model. Our experiments with the Qwen3 model family, over 6 languages, including up to 5 domains per language, demonstrates that fragment-based MT significantly outperforms alternative methods like standard k-shot, or drafting.</abstract>
    <identifier type="citekey">bouthors-etal-2026-reasoning</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.168/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>3546</start>
            <end>3566</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Reasoning about In-Context Samples for Machine-Translation
%A Bouthors, Maxime
%A Crego, Josep
%A Yvon, François
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F bouthors-etal-2026-reasoning
%X Large Language Models (LLMs) can be trained to perform chain-of-thoughts reasoning in order to improve the reliability of their responses. In this work, we investigate how explicit reasoning can be leveraged for Machine Translation (MT). We introduce a novel fragment-based reasoning framework in which the model first extracts parallel source-target fragments from retrieved similar examples, and uses these fragments as intermediate reasoning traces to produce the final translation. To train our model, we distill silver fragments and drafts from a larger teacher model. Our experiments with the Qwen3 model family, over 6 languages, including up to 5 domains per language, demonstrates that fragment-based MT significantly outperforms alternative methods like standard k-shot, or drafting.
%U https://aclanthology.org/2026.findings-emnlp.168/
%P 3546-3566

Download as File

Markdown (Informal)

[Reasoning about In-Context Samples for Machine-Translation](https://aclanthology.org/2026.findings-emnlp.168/) (Bouthors et al., Findings 2026)

Reasoning about In-Context Samples for Machine-Translation (Bouthors et al., Findings 2026)

ACL

Maxime Bouthors, Josep Crego, and François Yvon. 2026. Reasoning about In-Context Samples for Machine-Translation. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 3546–3566, Budapest, Hungary. Association for Computational Linguistics.