{"id":"https://openalex.org/W7133539559","doi":"https://doi.org/10.48550/arxiv.2603.02789","title":"OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale Datasets","display_name":"OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale Datasets","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133539559","doi":"https://doi.org/10.48550/arxiv.2603.02789"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.02789","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02789","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.02789","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122228782","display_name":"Jiyuan Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Jiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113302721","display_name":"Peiyue Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Peiyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128064069","display_name":"Atin Ghosh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ghosh, Atin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128053112","display_name":"Yifan Mai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mai, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002373633","display_name":"Daniel Dahlmeier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dahlmeier, Daniel","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4848000109195709,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4848000109195709,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.09860000014305115,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.052299998700618744,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7111999988555908},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6988999843597412},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5422999858856201},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48899999260902405},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.31859999895095825},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.3041999936103821}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8291000127792358},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7111999988555908},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6988999843597412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5771999955177307},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5422999858856201},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5343999862670898},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4359000027179718},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34529998898506165},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2802000045776367},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.02789","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02789","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.02789","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02789","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47786617279052734}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"enhance":[5,117],"the":[6,34],"potential":[7],"of":[8,36],"natural":[9],"language":[10,75],"processing.":[11],"However,":[12],"their":[13],"actual":[14],"impact":[15],"on":[16,54],"document":[17,133],"information":[18,56,134],"extraction":[19],"remains":[20],"unclear.":[21],"In":[22,40],"particular,":[23],"it":[24],"is":[25],"unclear":[26],"whether":[27],"an":[28,66],"MLLM-only":[29],"pipeline--while":[30],"simpler--can":[31],"truly":[32],"match":[33],"performance":[35,101],"traditional":[37],"OCR+MLLM":[38],"setups.":[39],"this":[41,122],"paper,":[42],"we":[43,64,106],"conduct":[44],"a":[45],"large-scale":[46],"benchmarking":[47],"study":[48],"that":[49,72,86,108],"evaluates":[50],"various":[51],"out-of-the-box":[52],"MLLMs":[53,118],"business-document":[55],"extraction.":[57,135],"To":[58],"examine":[59],"and":[60,113,128],"explore":[61],"failure":[62],"modes,":[63],"propose":[65],"automated":[67],"hierarchical":[68],"error":[69,80],"analysis":[70],"framework":[71],"leverages":[73],"large":[74],"models":[76],"(LLMs)":[77],"to":[78,102],"diagnose":[79],"patterns":[81],"systematically.":[82],"Our":[83],"findings":[84],"suggest":[85],"OCR":[87],"may":[88],"not":[89],"be":[90],"necessary":[91],"for":[92,131],"powerful":[93],"MLLMs,":[94],"as":[95],"image-only":[96],"input":[97],"can":[98,115,124],"achieve":[99],"comparable":[100],"OCR-enhanced":[103],"approaches.":[104],"Moreover,":[105],"demonstrate":[107],"carefully":[109],"designed":[110],"schema,":[111],"exemplars,":[112],"instructions":[114],"further":[116],"performance.":[119],"We":[120],"hope":[121],"work":[123],"offer":[125],"practical":[126],"guidance":[127],"valuable":[129],"insight":[130],"advancing":[132]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-05T00:00:00"}