{"id":"https://openalex.org/W7140073839","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.1","title":"Unveiling the Deficiencies of Pre-trained Text-and-Layout Models in Real-world Visually-rich Document Information Extraction","display_name":"Unveiling the Deficiencies of Pre-trained Text-and-Layout Models in Real-world Visually-rich Document Information Extraction","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140073839","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.1"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.1","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.1","pdf_url":"https://aclanthology.org/2026.findings-eacl.1.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.1.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130375890","display_name":"Chong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130330061","display_name":"Yixi Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixi Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013315914","display_name":"Yulu Xie","orcid":"https://orcid.org/0000-0003-0621-7748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yulu Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101301819","display_name":"Chenshu Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenshu Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130397731","display_name":"Yi Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Tu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130352991","display_name":"Ya Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ya Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109693861","display_name":"Mingxu Chai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingxu Chai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100308538","display_name":"Ziyu Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyu Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130349944","display_name":"Yue Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130381872","display_name":"Qi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.5773000121116638,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.5773000121116638,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0868000015616417,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.08380000293254852,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4555000066757202},{"id":"https://openalex.org/keywords/information-system","display_name":"Information system","score":0.31189998984336853},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.273499995470047},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.25060001015663147},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.24650000035762787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5756999850273132},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4555000066757202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35749998688697815},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33739998936653137},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29109999537467957},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25060001015663147},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.24650000035762787},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.23899999260902405}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.1","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.1","pdf_url":"https://aclanthology.org/2026.findings-eacl.1.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.1","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.1","pdf_url":"https://aclanthology.org/2026.findings-eacl.1.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140073839.pdf","grobid_xml":"https://content.openalex.org/works/W7140073839.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently":[0],"developed":[1],"pre-trained":[2],"text-and-layout":[3],"models":[4],"(PTLMs)":[5],"have":[6],"shown":[7],"remarkable":[8],"success":[9],"in":[10,88,181],"multiple":[11,156],"information":[12,122],"extraction":[13,123],"tasks":[14],"on":[15,24,73,76,192],"visually-rich":[16,125],"documents":[17,126],"(VrDs).However,":[18],"despite":[19],"achieving":[20],"extremely":[21],"high":[22],"performance":[23,28,75,101],"benchmarks,":[25],"their":[26,159],"real-world":[27,89,150,182],"falls":[29],"short":[30],"of":[31,66,86,102,108,142,153,195],"expectations.Owing":[32],"to":[33,42,63,81],"this":[34,111],"issue,":[35],"we":[36,113,147],"investigate":[37],"the":[38,74,84,93,99,105,130,139,144,149,193],"prevailing":[39,94],"evaluation":[40,70,95],"pipeline":[41,96],"reveal":[43],"that:":[44],"(1)":[45],"The":[46,69],"inadequate":[47],"annotations":[48,135],"within":[49],"benchmark":[50],"datasets":[51],"introduce":[52,114],"spurious":[53],"correlations":[54],"between":[55],"task":[56],"inputs":[57],"and":[58,78,133,167],"labels,":[59],"which":[60],"would":[61],"lead":[62],"overly-optimistic":[64],"estimation":[65],"model":[67],"performance.(2)":[68],"solely":[71],"relies":[72],"benchmarks":[77],"is":[79],"insufficient":[80],"comprehensively":[82],"explore":[83],"capabilities":[85,152],"methods":[87],"scenarios.These":[90],"problems":[91],"impede":[92],"from":[97,124,138,155],"reflecting":[98],"realworld":[100],"methods,":[103],"misleading":[104],"design":[106],"choices":[107],"method":[109],"optimization.In":[110],"work,":[112],"EC-FUNSD,":[115],"an":[116],"entity-centric":[117],"dataset":[118,128],"crafted":[119],"for":[120],"benchmarking":[121],"(VrD-IE).This":[127],"disentangles":[129],"falsely-coupled":[131],"segment":[132],"entity":[134],"that":[136,171,186],"arises":[137],"block-level":[140],"annotation":[141],"FUNSD.Using":[143],"proposed":[145],"dataset,":[146],"evaluate":[148],"VrD-IE":[151,183],"PTLMs":[154,173],"aspects,":[157],"including":[158],"absolute":[160],"performance,":[161],"as":[162,164,177,179],"well":[163,178],"generalization,":[165],"robustness":[166],"fairness.The":[168],"results":[169],"indicate":[170],"prevalent":[172],"do":[174],"not":[175],"perform":[176],"anticipated":[180],"scenarios.We":[184],"hope":[185],"our":[187],"study":[188],"can":[189],"inspire":[190],"reflection":[191],"directions":[194],"PTLM":[196],"development.":[197]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-24T00:00:00"}