# One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval Source: [One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval]() Collection index: [llms.txt]() Data updated: 2025-10-25T23:40:16.064Z Authors: Akari Asai, Xinyan Yu, Jungo Kasai, Hannaneh Hajishirzi Published: 2021-07-26T06:02:54.000Z ## Abstract We present Cross-lingual Open-Retrieval Answer Generation (CORA), the first unified many-to-many question answering (QA) model that can answer questions across many languages, even for ones without language-specific annotated data or knowledge sources. We introduce a new dense passage retrieval algorithm that is trained to retrieve documents across languages for a question. Combined with a multilingual autoregressive generation model, CORA answers directly in the target language without any translation or in-language retrieval modules as used in prior work. We propose an iterative training method that automatically extends annotated data available only in high-resource languages to low-resource ones. Our results show that CORA substantially outperforms the previous state of the art on multilingual open QA benchmarks across 26 languages, 9 of which are unseen during training. Our analyses show the significance of cross-lingual retrieval and generation in many languages, particularly under low-resource settings. ## 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. - [Cross-lingual retrieval on MKQA](): Cross-lingual retrieval; MKQA; Avg. Recall@100: 59.8. ## Original sources and implementation [Original paper]() [PDF]()