{"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/document-understanding-dataset-and-evaluation","title":"Document Understanding Dataset and Evaluation (DUDE)","arxiv_id":"2305.08455","date":"2023-05-15","proceeding":"ICCV 2023 1","authors":["Jordy Van Landeghem","Rubén Tito","Łukasz Borchmann","Michał Pietruszka","Paweł Józiak","Rafał Powalski","Dawid Jurkiewicz","Mickaël Coustaty","Bertrand Ackaert","Ernest Valveny","Matthew Blaschko","Sien Moens","Tomasz Stanisławek"],"abstract":"We call on the Document AI (DocAI) community to reevaluate current methodologies and embrace the challenge of creating more practically-oriented benchmarks. Document Understanding Dataset and Evaluation (DUDE) seeks to remediate the halted research progress in understanding visually-rich documents (VRDs). We present a new dataset with novelties related to types of questions, answers, and document layouts based on multi-industry, multi-domain, and multi-page VRDs of various origins, and dates. Moreover, we are pushing the boundaries of current methods by creating multi-task and multi-domain evaluation setups that more accurately simulate real-world situations where powerful generalization and adaptation under low-resource settings are desired. DUDE aims to set a new standard as a more practical, long-standing benchmark for the community, and we hope that it will lead to future extensions and contributions that address real-world challenges. Finally, our work illustrates the importance of finding more efficient ways to model language, images, and layout in DocAI.","url_abs":"https://arxiv.org/abs/2305.08455v3","url_pdf":"https://arxiv.org/pdf/2305.08455v3.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":"document-understanding-dataset-and-evaluation","repo_url":"https://github.com/rubenpt91/MP-DocVQA-Framework","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"document-ai","task_name":"Document AI"},{"task_slug":"document-understanding","task_name":"document understanding"}],"methods":[{"method_slug":"adafactor","method_name":"Adafactor"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"glu","method_name":"Gated Linear Unit"},{"method_slug":"inverse-square-root-schedule","method_name":"Inverse Square Root Schedule"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sentencepiece","method_name":"SentencePiece"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"t5","method_name":"T5"}],"datasets_introduced":[{"slug":"dude","name":"DUDE","full_name":"Document UnderstanDing of Everything"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.08455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.08455"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rubenpt91/MP-DocVQA-Framework","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"88a281f34cff4e96","entry":"build_dataset","repo":"rubenpt91/MP-DocVQA-Framework","repo_kind":"official","path":"build_utils.py","file_url":"https://github.com/rubenpt91/MP-DocVQA-Framework/blob/HEAD/build_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88a281f34cff4e96"}},{"code_sha256_prefix":"2d363ded709cf8c9","entry":"build_model","repo":"rubenpt91/MP-DocVQA-Framework","repo_kind":"official","path":"build_utils.py","file_url":"https://github.com/rubenpt91/MP-DocVQA-Framework/blob/HEAD/build_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d363ded709cf8c9"}},{"code_sha256_prefix":"d7bf1e31e1918784","entry":"build_optimizer","repo":"rubenpt91/MP-DocVQA-Framework","repo_kind":"official","path":"build_utils.py","file_url":"https://github.com/rubenpt91/MP-DocVQA-Framework/blob/HEAD/build_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d7bf1e31e1918784"}},{"code_sha256_prefix":"74216735ae11b6fd","entry":"mpdocvqa_collate_fn","repo":"rubenpt91/MP-DocVQA-Framework","repo_kind":"official","path":"datasets/MP_DocVQA.py","file_url":"https://github.com/rubenpt91/MP-DocVQA-Framework/blob/HEAD/datasets/MP_DocVQA.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"74216735ae11b6fd"}},{"code_sha256_prefix":"d7daacc3e799e5e2","entry":"singlepage_docvqa_collate_fn","repo":"rubenpt91/MP-DocVQA-Framework","repo_kind":"official","path":"datasets/SP_DocVQA.py","file_url":"https://github.com/rubenpt91/MP-DocVQA-Framework/blob/HEAD/datasets/SP_DocVQA.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d7daacc3e799e5e2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}