# Few-Shot Multilingual Open-Domain QA from 5 Examples

Source: [Few-Shot Multilingual Open-Domain QA from 5 Examples](<https://www.sota2.com/research/paper/68fa772e1e209131cea719fd>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:11:54.790Z

Authors: Fan Jiang, Tom Drummond, Trevor Cohn

Published: 2025-02-27T03:24:57.000Z

## 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 \\emph{few-shot learning} approach to synthesise 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, \\textsc{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 \\emph{cross-lingual prompting} strategy with only English-supervised data, making it a general and applicable solution for MLODQA tasks without costly large-scale annotation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2502.19722>)

[PDF](<https://arxiv.org/pdf/2502.19722.pdf>)
