{"url":"/dataset/xcopa","name":"XCOPA","full_name":null,"description_markdown":"The Cross-lingual Choice of Plausible Alternatives (**XCOPA**) dataset is a benchmark to evaluate the ability of machine learning models to transfer commonsense reasoning across languages. The dataset is the translation and reannotation of the English COPA (Roemmele et al. 2011) and covers 11 languages from 11 families and several areas around the globe. The dataset is challenging as it requires both the command of world knowledge and the ability to generalise to new languages.\n\nSource: [https://github.com/cambridgeltl/xcopa](https://github.com/cambridgeltl/xcopa)","description_withheld":null,"homepage":"https://github.com/cambridgeltl/xcopa","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/xcopa-a-multilingual-dataset-for-causal","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","first_author":"Edoardo Maria Ponti","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Cross-Lingual Transfer","url":"/task/cross-lingual-transfer","datasets_with_task":"/datasets/task/cross-lingual-transfer"}],"languages":[],"variants":["XCOPA"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/cambridgeltl/xcopa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/juletxara/xcopa_mt","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/xcopa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/cambridgeltl/xcopa","url":"https://github.com/cambridgeltl/xcopa","frameworks":[]}],"num_papers_in_archive":110,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/cross-lingual-transfer-on-xcopa","task":"Cross-Lingual Transfer","dataset_variant":"XCOPA","rows":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PaLM 2 (few-shot)","paper":"/paper/palm-2-technical-report-1","metrics":{"Accuracy":"94.4"},"code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/crosslingual-generalization-through-multitask","title":"Crosslingual Generalization through Multitask Finetuning","date":"2022-11-03","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mgpt-few-shot-learners-go-multilingual","title":"mGPT: Few-Shot Learners Go Multilingual","date":"2022-04-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/xcopa-a-multilingual-dataset-for-causal","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","date":"2020-05-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mad-x-an-adapter-based-framework-for-multi","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","date":"2020-04-30","rows_on_this_dataset":1,"code_links":3,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":4,"samples_ran":1,"samples_unverified":3,"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."}