<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2025-shot">
    <titleInfo>
        <title>Few-Shot Multilingual Open-Domain QA from Five Examples</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Fan</namePart>
        <namePart type="family">Jiang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tom</namePart>
        <namePart type="family">Drummond</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Trevor</namePart>
        <namePart type="family">Cohn</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Recent approaches to multilingual open- domain question answering (MLODQA) have achieved promising results given abundant language-specific training data. However, the considerable annotation cost limits the application of these methods for underrepresented languages. We introduce a few-shot learning approach to synthesize large-scale multilingual data from large language models (LLMs). Our method begins with large-scale self-supervised pre-training using WikiData, followed by training on high-quality synthetic multilingual data generated by prompting LLMs with few-shot supervision. The final model, FsModQA, significantly outperforms existing few-shot and supervised baselines in MLODQA and cross-lingual and monolingual retrieval. We further show our method can be extended for effective zero-shot adaptation to new languages through a cross-lingual prompting strategy with only English-supervised data, making it a general and applicable solution for MLODQA tasks without costly large-scale annotation.</abstract>
    <identifier type="citekey">jiang-etal-2025-shot</identifier>
    <identifier type="doi">10.1162/tacl_a_00750</identifier>
    <location>
        <url>https://aclanthology.org/2025.tacl-1.24/</url>
    </location>
    <part>
        <date>2025</date>
        <detail type="volume"><number>13</number></detail>
        <extent unit="page">
            <start>481</start>
            <end>504</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Few-Shot Multilingual Open-Domain QA from Five Examples
%A Jiang, Fan
%A Drummond, Tom
%A Cohn, Trevor
%J Transactions of the Association for Computational Linguistics
%D 2025
%V 13
%I MIT Press
%C Cambridge, MA
%F jiang-etal-2025-shot
%X Recent approaches to multilingual open- domain question answering (MLODQA) have achieved promising results given abundant language-specific training data. However, the considerable annotation cost limits the application of these methods for underrepresented languages. We introduce a few-shot learning approach to synthesize large-scale multilingual data from large language models (LLMs). Our method begins with large-scale self-supervised pre-training using WikiData, followed by training on high-quality synthetic multilingual data generated by prompting LLMs with few-shot supervision. The final model, FsModQA, significantly outperforms existing few-shot and supervised baselines in MLODQA and cross-lingual and monolingual retrieval. We further show our method can be extended for effective zero-shot adaptation to new languages through a cross-lingual prompting strategy with only English-supervised data, making it a general and applicable solution for MLODQA tasks without costly large-scale annotation.
%R 10.1162/tacl_a_00750
%U https://aclanthology.org/2025.tacl-1.24/
%U https://doi.org/10.1162/tacl_a_00750
%P 481-504

Markdown (Informal)

[Few-Shot Multilingual Open-Domain QA from Five Examples](https://aclanthology.org/2025.tacl-1.24/) (Jiang et al., TACL 2025)

• Few-Shot Multilingual Open-Domain QA from Five Examples (Jiang et al., TACL 2025)

ACL

• Fan Jiang, Tom Drummond, and Trevor Cohn. 2025. Few-Shot Multilingual Open-Domain QA from Five Examples. Transactions of the Association for Computational Linguistics, 13:481–504.