{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/layoutxlm-multimodal-pre-training-for","title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","arxiv_id":"2104.08836","date":"2021-04-18","proceeding":null,"authors":["Yiheng Xu","Tengchao Lv","Lei Cui","Guoxin Wang","Yijuan Lu","Dinei Florencio","Cha Zhang","Furu Wei"],"abstract":"Multimodal pre-training with text, layout, and image has achieved SOTA performance for visually-rich document understanding tasks recently, which demonstrates the great potential for joint learning across different modalities. In this paper, we present LayoutXLM, a multimodal pre-trained model for multilingual document understanding, which aims to bridge the language barriers for visually-rich document understanding. To accurately evaluate LayoutXLM, we also introduce a multilingual form understanding benchmark dataset named XFUND, which includes form understanding samples in 7 languages (Chinese, Japanese, Spanish, French, Italian, German, Portuguese), and key-value pairs are manually labeled for each language. Experiment results show that the LayoutXLM model has significantly outperformed the existing SOTA cross-lingual pre-trained models on the XFUND dataset. The pre-trained LayoutXLM model and the XFUND dataset are publicly available at https://aka.ms/layoutxlm.","url_abs":"https://arxiv.org/abs/2104.08836v3","url_pdf":"https://arxiv.org/pdf/2104.08836v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"layoutxlm-multimodal-pre-training-for","repo_url":"https://github.com/microsoft/unilm/tree/master/layoutxlm","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"layoutxlm-multimodal-pre-training-for","repo_url":"https://github.com/facebookresearch/data2vec_vision","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"layoutxlm-multimodal-pre-training-for","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"layoutxlm-multimodal-pre-training-for","repo_url":"https://github.com/2024-MindSpore-1/Code3/tree/main/VI-LayoutXLM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"layoutxlm-multimodal-pre-training-for","repo_url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/layoutxlm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"layoutxlm-multimodal-pre-training-for","repo_url":"https://github.com/PaddlePaddle/PaddleOCR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"document-image-classification","task_name":"Document Image Classification"},{"task_slug":"form","task_name":"Form"},{"task_slug":"key-value-pair-extraction","task_name":"Key-value Pair Extraction"},{"task_slug":"document-understanding","task_name":"document understanding"}],"methods":[],"datasets_introduced":[{"slug":"xfun","name":"XFUND","full_name":"A Multilingual Form Understanding Benchmark"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/document-image-classification-on-rvl-cdip","task":"Document Image Classification","dataset":"RVL-CDIP","model":"LayoutXLM","rank_in_archive_order":13,"of":31,"metrics":{"Accuracy":"95.21%"},"uses_additional_data":false},{"leaderboard":"/sota/key-value-pair-extraction-on-rfund-en","task":"Key-value Pair Extraction","dataset":"RFUND-EN","model":"LayoutXLM_base","rank_in_archive_order":9,"of":13,"metrics":{"key-value pair F1":"53.98"},"uses_additional_data":false},{"leaderboard":"/sota/key-value-pair-extraction-on-sibr","task":"Key-value Pair Extraction","dataset":"SIBR","model":"LayoutXLM","rank_in_archive_order":6,"of":7,"metrics":{"key-value pair F1":"70.45"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.08836","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}