{"url":"/dataset/xquad","name":"XQuAD","full_name":"XQuAD","description_markdown":"XQuAD (Cross-lingual Question Answering Dataset) is a benchmark dataset for evaluating cross-lingual question answering performance. The dataset consists of a subset of 240 paragraphs and 1190 question-answer pairs from the development set of SQuAD v1.1 (Rajpurkar et al., 2016) together with their professional translations into ten languages: Spanish, German, Greek, Russian, Turkish, Arabic, Vietnamese, Thai, Chinese, and Hindi. Consequently, the dataset is entirely parallel across 11 languages.\r\n\r\nSource: [XQuAD](https://github.com/deepmind/xquad)\r\nImage Source: [https://arxiv.org/pdf/1910.11856v3.pdf](https://arxiv.org/pdf/1910.11856v3.pdf)","description_withheld":null,"homepage":"https://github.com/deepmind/xquad","introduced_date":"2019-10-25","introduced_date_note":null,"introduced_by":{"paper":"/paper/on-the-cross-lingual-transferability-of","title":"On the Cross-lingual Transferability of Monolingual Representations","first_author":"Mikel Artetxe","url":null},"license":{"name":"CC BY-SA 4.0","url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"},{"name":"Cross-Lingual Question Answering","url":"/task/cross-lingual-question-answering","datasets_with_task":"/datasets/task/cross-lingual-question-answering"}],"languages":[{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"German","url":"/datasets/language/german"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Multilingual","url":"/datasets/language/multilingual"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Arabic","url":"/datasets/language/arabic"},{"name":"Hindi","url":"/datasets/language/hindi"},{"name":"Thai","url":"/datasets/language/thai"},{"name":"Turkish","url":"/datasets/language/turkish"},{"name":"Vietnamese","url":"/datasets/language/vietnamese"},{"name":"Greek","url":"/datasets/language/greek"}],"variants":["XQuAD","XQuAD (de)"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/xquad","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/juletxara/xquad_xtreme","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/google/xquad","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/xquad","frameworks":["tf","jax"]},{"repo":"https://github.com/deepmind/xquad","url":"https://github.com/deepmind/xquad","frameworks":[]}],"num_papers_in_archive":190,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/cross-lingual-question-answering-on-xquad","task":"Cross-Lingual Question Answering","dataset_variant":"XQuAD","rows":4,"metrics":["EM","F1","Average F1"],"first_row_in_archive_order":{"model":"ByT5 XXL","paper":"/paper/byt5-towards-a-token-free-future-with-pre","metrics":{"EM":"63.6","F1":"79.7"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers/tree/master/src/transformers/models/byt5"},{"title":"google-research/byt5","url":"https://github.com/google-research/byt5"},{"title":"ufal/multilexnorm2021","url":"https://github.com/ufal/multilexnorm2021"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/byt5"},{"title":"yoreG123/Paddle-ByT5","url":"https://github.com/yoreG123/Paddle-ByT5"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mluke-the-power-of-entity-representations-in","title":"mLUKE: The Power of Entity Representations in Multilingual Pretrained Language Models","date":"2021-10-15","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/byt5-towards-a-token-free-future-with-pre","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","date":"2021-05-28","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":6,"samples_ran":1,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rethinking-embedding-coupling-in-pre-trained-1","title":"Rethinking embedding coupling in pre-trained language models","date":"2020-10-24","rows_on_this_dataset":2,"code_links":4,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":1,"samples_harvested":6,"samples_ran":1,"samples_unverified":5,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}