{"url":"/task/key-value-pair-extraction","name":"Key-value Pair Extraction","slug":"key-value-pair-extraction","description_markdown":"Extract key-value pairs from a form-like document. \r\n\r\nA prediction is considered TP if the predicted key and value contents match the ground truths. Key-value pair F1-score is employed as the metric.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":12,"papers_with_code":9,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/key-value-pair-extraction-on-rfund-en","slug":"key-value-pair-extraction-on-rfund-en","dataset":"RFUND-EN","dataset_url":"/dataset/rfund-en","rows_in_archive":13,"metrics":["key-value pair F1"],"first_row_in_archive_order":{"model":"PEneo\n(LayoutLMv3_base)","paper_title":"PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction","paper_url":"/paper/peneo-unifying-line-extraction-line-grouping","paper_date":"2024-01-07","arxiv_id":"2401.03472","code_links":[{"title":"ZeningLin/PEneo","url":"https://github.com/ZeningLin/PEneo"}],"syntology":null}},{"leaderboard":"/sota/key-value-pair-extraction-on-sibr","slug":"key-value-pair-extraction-on-sibr","dataset":"SIBR","dataset_url":"/dataset/sibr","rows_in_archive":7,"metrics":["key-value pair F1"],"first_row_in_archive_order":{"model":"PEneo\n(LayoutLMv3_base_chinese)","paper_title":"PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction","paper_url":"/paper/peneo-unifying-line-extraction-line-grouping","paper_date":"2024-01-07","arxiv_id":"2401.03472","code_links":[{"title":"ZeningLin/PEneo","url":"https://github.com/ZeningLin/PEneo"}],"syntology":null}}],"datasets":[{"url":"/dataset/sibr","name":"SIBR","full_name":"SIBR Dataset for VIE in the Wild","num_papers_in_archive":14},{"url":"/dataset/rfund","name":"RFUND","full_name":"Revised FUNSD and XFUND","num_papers_in_archive":8},{"url":"/dataset/rfund-en","name":"RFUND-EN","full_name":"","num_papers_in_archive":8}],"subtasks":[],"parent_tasks":[{"url":"/task/key-information-extraction","name":"Key Information Extraction"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":9,"of":9,"tagged_in_all":12,"items":[{"url":"/paper/layoutlmv2-multi-modal-pre-training-for","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","date":"2020-12-29","arxiv_id":"2012.14740","repositories_listed":9,"syntology":null},{"url":"/paper/layoutxlm-multimodal-pre-training-for","title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","date":"2021-04-18","arxiv_id":"2104.08836","repositories_listed":6,"syntology":null},{"url":"/paper/lilt-a-simple-yet-effective-language","title":"LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding","date":"2022-02-28","arxiv_id":"2202.13669","repositories_listed":5,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/donut-document-understanding-transformer","title":"OCR-free Document Understanding Transformer","date":"2021-11-30","arxiv_id":"2111.15664","repositories_listed":5,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/layoutlmv3-pre-training-for-document-ai-with","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","date":"2022-04-18","arxiv_id":"2204.08387","repositories_listed":4,"syntology":null},{"url":"/paper/reading-order-matters-information-extraction","title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","date":"2023-10-17","arxiv_id":"2310.11016","repositories_listed":2,"syntology":null},{"url":"/paper/kvp10k-a-comprehensive-dataset-for-key-value","title":"KVP10k : A Comprehensive Dataset for Key-Value Pair Extraction in Business Documents","date":"2024-05-01","arxiv_id":"2405.00505","repositories_listed":1,"syntology":null},{"url":"/paper/peneo-unifying-line-extraction-line-grouping","title":"PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction","date":"2024-01-07","arxiv_id":"2401.03472","repositories_listed":1,"syntology":null},{"url":"/paper/geolayoutlm-geometric-pre-training-for-visual","title":"GeoLayoutLM: Geometric Pre-training for Visual Information Extraction","date":"2023-04-21","arxiv_id":"2304.10759","repositories_listed":1,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}