{"url":"/dataset/xfun","name":"XFUND","full_name":"A Multilingual Form Understanding Benchmark","description_markdown":"XFUND is a multilingual form understanding benchmark dataset that includes human-labeled forms with key-value pairs in 7 languages (Chinese, Japanese, Spanish, French, Italian, German, Portuguese).","description_withheld":null,"homepage":"https://github.com/doc-analysis/XFUND","introduced_date":"2021-04-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/layoutxlm-multimodal-pre-training-for","title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","first_author":"Yiheng Xu","url":null},"license":{"name":"CC BY-NC-SA 4.0","url":null},"modalities":[],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Relation Extraction","url":"/task/relation-extraction","datasets_with_task":"/datasets/task/relation-extraction"},{"name":"Relation Linking","url":"/task/relation-linking","datasets_with_task":"/datasets/task/relation-linking"},{"name":"Multilingual Named Entity Recognition","url":"/task/multilingual-named-entity-recognition","datasets_with_task":"/datasets/task/multilingual-named-entity-recognition"}],"languages":[{"name":"French","url":"/datasets/language/french"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"German","url":"/datasets/language/german"},{"name":"Italian","url":"/datasets/language/italian"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Japanese","url":"/datasets/language/japanese"},{"name":"Portuguese","url":"/datasets/language/portuguese"}],"variants":["XFUND"],"data_loaders":[],"num_papers_in_archive":20,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"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."}