RozarNLP-cr7 at WMT 2026: LoRA-Fine-Tuned NLLB for Low-Resource Machine Translation in Northeastern Indian Languages

Suyash Yadav; Utkarsh Chaudhary; Alapan Kuila

RozarNLP-cr7 at WMT 2026: LoRA-Fine-Tuned NLLB for Low-Resource Machine Translation in Northeastern Indian Languages

Suyash Yadav, Utkarsh Chaudhary, Alapan Kuila

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 present constrained WMT 2026 submissions for low-resource Northeastern Indian languages using NLLB-200 Distilled 1.3B with multilingual LoRA adapters trained only on the official organizer-provided parallel data. The adapted systems improve over the submitted baselines for both Mizo directions and Bengali-script Manipuri→English, but show substantial variation across languages and directions. We further manually analyze approximately 100 Indic→English outputs and validate the systems on WMT 2025 data, highlighting generation artifacts and the challenges of parameter-efficient adaptation across languages, scripts, and translation directions.

Anthology ID:: 2026.wmt-main.165
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:: 2247–2254
Language:
URL:: https://aclanthology.org/2026.wmt-main.165/
DOI:
Bibkey:
Cite (ACL):: Suyash Yadav, Utkarsh Chaudhary, and Alapan Kuila. 2026. RozarNLP-cr7 at WMT 2026: LoRA-Fine-Tuned NLLB for Low-Resource Machine Translation in Northeastern Indian Languages. In Proceedings of the Eleventh Conference on Machine Translation, pages 2247–2254, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: RozarNLP-cr7 at WMT 2026: LoRA-Fine-Tuned NLLB for Low-Resource Machine Translation in Northeastern Indian Languages (Yadav et al., WMT 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.wmt-main.165.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{yadav-etal-2026-rozarnlp,
    title = "{R}ozar{NLP}-cr7 at {WMT} 2026: {L}o{RA}-Fine-Tuned {NLLB} for Low-Resource Machine Translation in {N}ortheastern {I}ndian Languages",
    author = "Yadav, Suyash  and
      Chaudhary, Utkarsh  and
      Kuila, Alapan",
    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.165/",
    pages = "2247--2254",
    ISBN = "979-8-89176-474-3",
    abstract = "We present constrained WMT 2026 submissions for low-resource Northeastern Indian languages using NLLB-200 Distilled 1.3B with multilingual LoRA adapters trained only on the official organizer-provided parallel data. The adapted systems improve over the submitted baselines for both Mizo directions and Bengali-script Manipuri{\textrightarrow}English, but show substantial variation across languages and directions. We further manually analyze approximately 100 Indic{\textrightarrow}English outputs and validate the systems on WMT 2025 data, highlighting generation artifacts and the challenges of parameter-efficient adaptation across languages, scripts, and translation directions."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yadav-etal-2026-rozarnlp">
    <titleInfo>
        <title>RozarNLP-cr7 at WMT 2026: LoRA-Fine-Tuned NLLB for Low-Resource Machine Translation in Northeastern Indian Languages</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Suyash</namePart>
        <namePart type="family">Yadav</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Utkarsh</namePart>
        <namePart type="family">Chaudhary</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alapan</namePart>
        <namePart type="family">Kuila</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 present constrained WMT 2026 submissions for low-resource Northeastern Indian languages using NLLB-200 Distilled 1.3B with multilingual LoRA adapters trained only on the official organizer-provided parallel data. The adapted systems improve over the submitted baselines for both Mizo directions and Bengali-script Manipuri→English, but show substantial variation across languages and directions. We further manually analyze approximately 100 Indic→English outputs and validate the systems on WMT 2025 data, highlighting generation artifacts and the challenges of parameter-efficient adaptation across languages, scripts, and translation directions.</abstract>
    <identifier type="citekey">yadav-etal-2026-rozarnlp</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.165/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>2247</start>
            <end>2254</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T RozarNLP-cr7 at WMT 2026: LoRA-Fine-Tuned NLLB for Low-Resource Machine Translation in Northeastern Indian Languages
%A Yadav, Suyash
%A Chaudhary, Utkarsh
%A Kuila, Alapan
%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 yadav-etal-2026-rozarnlp
%X We present constrained WMT 2026 submissions for low-resource Northeastern Indian languages using NLLB-200 Distilled 1.3B with multilingual LoRA adapters trained only on the official organizer-provided parallel data. The adapted systems improve over the submitted baselines for both Mizo directions and Bengali-script Manipuri→English, but show substantial variation across languages and directions. We further manually analyze approximately 100 Indic→English outputs and validate the systems on WMT 2025 data, highlighting generation artifacts and the challenges of parameter-efficient adaptation across languages, scripts, and translation directions.
%U https://aclanthology.org/2026.wmt-main.165/
%P 2247-2254

Download as File

Markdown (Informal)

[RozarNLP-cr7 at WMT 2026: LoRA-Fine-Tuned NLLB for Low-Resource Machine Translation in Northeastern Indian Languages](https://aclanthology.org/2026.wmt-main.165/) (Yadav et al., WMT 2026)

RozarNLP-cr7 at WMT 2026: LoRA-Fine-Tuned NLLB for Low-Resource Machine Translation in Northeastern Indian Languages (Yadav et al., WMT 2026)

ACL

Suyash Yadav, Utkarsh Chaudhary, and Alapan Kuila. 2026. RozarNLP-cr7 at WMT 2026: LoRA-Fine-Tuned NLLB for Low-Resource Machine Translation in Northeastern Indian Languages. In Proceedings of the Eleventh Conference on Machine Translation, pages 2247–2254, Budapest, Hungary. Association for Computational Linguistics.