Lightweight Cross-Lingual Federated Prompt Tuning for Low-Resource Languages

Ubaid Azam; Imran Razzak; Shoaib Jameel

doi:10.63317/3qfz4ob3zbo8

Lightweight Cross-Lingual Federated Prompt Tuning for Low-Resource Languages

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 external publication .)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Multilingual NLP faces challenges of data heterogeneity, privacy, and limited computational resources, especially for low-resource languages. Centralised methods risk privacy breaches, while federated learning struggles with communication overhead and poor cross-lingual generalisation. We propose FLiP (Federated Lightweight Prompt-tuning), a privacy-preserving, resource-efficient, generalizable framework integrating prompt-based learning with federated optimisation. FLiP eliminates communication overhead, reduces trainable parameters to 16%, and cuts GPU memory use by 90%. Experiments show superior generalisation and efficiency under both IID and Non-IID settings, establishing FLiP as a scalable, privacy-aware solution for multilingual NLP, particularly in low-resource and indigenous language contexts.

Anthology ID:: 2026.lrec-1.260
Volume:: Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:: May
Year:: 2026
Address:: Palma de Mallorca, Spain
Editors:: Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:: LREC
SIG:
Publisher:: ELRA Language Resource Association
Note:
Pages:: 3304–3316
Language:
External URL:: https://lrec.elra.info/lrec2026-main-260
DOI:: 10.63317/3qfz4ob3zbo8
Bibkey:
Cite (ACL):: Ubaid Azam, Imran Razzak, and Shoaib Jameel. 2026. Lightweight Cross-Lingual Federated Prompt Tuning for Low-Resource Languages. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 3304–3316, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):: Lightweight Cross-Lingual Federated Prompt Tuning for Low-Resource Languages (Azam et al., LREC 2026)
Copy Citation:

External Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{azam-etal-2026-lightweight,
    title = "Lightweight Cross-Lingual Federated Prompt Tuning for Low-Resource Languages",
    author = "Azam, Ubaid  and
      Razzak, Imran  and
      Jameel, Shoaib",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://aclanthology.org/2026.lrec-1.260/",
    doi = "10.63317/3qfz4ob3zbo8",
    pages = "3304--3316",
    abstract = "Multilingual NLP faces challenges of data heterogeneity, privacy, and limited computational resources, especially for low-resource languages. Centralised methods risk privacy breaches, while federated learning struggles with communication overhead and poor cross-lingual generalisation. We propose FLiP (Federated Lightweight Prompt-tuning), a privacy-preserving, resource-efficient, generalizable framework integrating prompt-based learning with federated optimisation. FLiP eliminates communication overhead, reduces trainable parameters to 16{\%}, and cuts GPU memory use by 90{\%}. Experiments show superior generalisation and efficiency under both IID and Non-IID settings, establishing FLiP as a scalable, privacy-aware solution for multilingual NLP, particularly in low-resource and indigenous language contexts."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="azam-etal-2026-lightweight">
    <titleInfo>
        <title>Lightweight Cross-Lingual Federated Prompt Tuning for Low-Resource Languages</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ubaid</namePart>
        <namePart type="family">Azam</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Imran</namePart>
        <namePart type="family">Razzak</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shoaib</namePart>
        <namePart type="family">Jameel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Multilingual NLP faces challenges of data heterogeneity, privacy, and limited computational resources, especially for low-resource languages. Centralised methods risk privacy breaches, while federated learning struggles with communication overhead and poor cross-lingual generalisation. We propose FLiP (Federated Lightweight Prompt-tuning), a privacy-preserving, resource-efficient, generalizable framework integrating prompt-based learning with federated optimisation. FLiP eliminates communication overhead, reduces trainable parameters to 16%, and cuts GPU memory use by 90%. Experiments show superior generalisation and efficiency under both IID and Non-IID settings, establishing FLiP as a scalable, privacy-aware solution for multilingual NLP, particularly in low-resource and indigenous language contexts.</abstract>
    <identifier type="citekey">azam-etal-2026-lightweight</identifier>
    <identifier type="doi">10.63317/3qfz4ob3zbo8</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.260/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>3304</start>
            <end>3316</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Lightweight Cross-Lingual Federated Prompt Tuning for Low-Resource Languages
%A Azam, Ubaid
%A Razzak, Imran
%A Jameel, Shoaib
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F azam-etal-2026-lightweight
%X Multilingual NLP faces challenges of data heterogeneity, privacy, and limited computational resources, especially for low-resource languages. Centralised methods risk privacy breaches, while federated learning struggles with communication overhead and poor cross-lingual generalisation. We propose FLiP (Federated Lightweight Prompt-tuning), a privacy-preserving, resource-efficient, generalizable framework integrating prompt-based learning with federated optimisation. FLiP eliminates communication overhead, reduces trainable parameters to 16%, and cuts GPU memory use by 90%. Experiments show superior generalisation and efficiency under both IID and Non-IID settings, establishing FLiP as a scalable, privacy-aware solution for multilingual NLP, particularly in low-resource and indigenous language contexts.
%R 10.63317/3qfz4ob3zbo8
%U https://aclanthology.org/2026.lrec-1.260/
%U https://doi.org/10.63317/3qfz4ob3zbo8
%P 3304-3316

Download as File

Markdown (Informal)

[Lightweight Cross-Lingual Federated Prompt Tuning for Low-Resource Languages](https://aclanthology.org/2026.lrec-1.260/) (Azam et al., LREC 2026)

Lightweight Cross-Lingual Federated Prompt Tuning for Low-Resource Languages (Azam et al., LREC 2026)

ACL

Ubaid Azam, Imran Razzak, and Shoaib Jameel. 2026. Lightweight Cross-Lingual Federated Prompt Tuning for Low-Resource Languages. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 3304–3316, Palma de Mallorca, Spain. ELRA Language Resource Association.