@article{jiang-etal-2025-shot,
    title = "Few-Shot Multilingual Open-Domain {QA} from Five Examples",
    author = "Jiang, Fan  and
      Drummond, Tom  and
      Cohn, Trevor",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "13",
    year = "2025",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/corrections-2025-07/2025.tacl-1.24/",
    doi = "10.1162/tacl_a_00750",
    pages = "481--504",
    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."
}