{"id":"https://openalex.org/W4416046366","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2047","title":"MMTabReal: Real-World Benchmark for Multimodal Table Understanding","display_name":"MMTabReal: Real-World Benchmark for Multimodal Table Understanding","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416046366","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2047"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.2047","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2047","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2047","pdf_url":"https://aclanthology.org/2026.findings-acl.2047.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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: ACL 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-acl.2047.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094304478","display_name":"Prasham Titiya","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasham Yatinkumar Titiya","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jainil Trivedi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jainil Trivedi","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083735830","display_name":"Chitta R. Baral","orcid":"https://orcid.org/0000-0002-7549-723X","observed_orcids":["https://orcid.org/0000-0002-7549-723X"]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chitta Baral","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":null,"display_name":"Vivek Gupta","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivek Gupta","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00982346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"41156","last_page":"41176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.00019999999494757503,"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":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/table-understanding","display_name":"table understanding","score":0.722000002861023},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9639999866485596},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.7139999866485596},{"id":"https://openalex.org/keywords/visual-grounding","display_name":"visual grounding","score":0.6859999895095825},{"id":"https://openalex.org/keywords/spatial-alignment","display_name":"spatial alignment","score":0.9819999933242798},{"id":"https://openalex.org/keywords/multi-step-reasoning","display_name":"multi-step reasoning","score":0.8980000019073486},{"id":"https://openalex.org/keywords/tabular-reasoning","display_name":"tabular reasoning","score":0.5619999766349792},{"id":"https://openalex.org/keywords/question-answering","display_name":"question answering","score":0.460999995470047},{"id":"https://openalex.org/keywords/vision-language-fusion","display_name":"vision-language fusion","score":0.4869999885559082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7404000163078308},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6815999746322632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5406000018119812},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5152999758720398},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3968000113964081},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3287999927997589},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27709999680519104},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26249998807907104}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.2047","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2047","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2047","pdf_url":"https://aclanthology.org/2026.findings-acl.2047.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.21771","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.21771","pdf_url":"https://arxiv.org/pdf/2505.21771","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.21771","doi":"https://doi.org/10.48550/arxiv.2505.21771","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.21771","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.2047","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2047","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2047","pdf_url":"https://aclanthology.org/2026.findings-acl.2047.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309835","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416046366.pdf","grobid_xml":"https://content.openalex.org/works/W4416046366.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4399657497","https://openalex.org/W7152598570","https://openalex.org/W7166870515","https://openalex.org/W4415183329","https://openalex.org/W7140112893","https://openalex.org/W7160335161","https://openalex.org/W4413145115","https://openalex.org/W7125937094","https://openalex.org/W4416034101","https://openalex.org/W7214749342"],"abstract_inverted_index":{"Multimodal":[0,22],"tables":[1,52],"i.e.":[2],"tabular":[3,104],"layouts":[4],"interleaved":[5],"with":[6,54,84,103],"charts,":[7],"maps,":[8],"icons,":[9],"and":[10,30,65,81,106,126,133],"color":[11],"encodings":[12],"are":[13,135],"ubiquitous":[14],"in":[15,28,76],"real":[16],"applications":[17],"yet":[18],"remain":[19],"difficult":[20],"for":[21,96,113],"Large":[23],"Language":[24],"Models":[25],"(MLLMs).Despite":[26],"advances":[27],"text":[29],"image":[31],"understanding,":[32],"systematic":[33],"evaluation":[34,114],"of":[35,49,69,129],"table-centric":[36],"multimodal":[37,131],"reasoning":[38,63,127],"is":[39,111],"limited.We":[40],"introduce":[41],"MMTABREAL,":[42],"a":[43,117],"MultiModal":[44],"Table":[45],"Benchmark,":[46],"human-curated":[47],"suite":[48],"500":[50],"real-world":[51,130],"paired":[53],"4,021":[55],"question-answer":[56],"pairs.MMTABREAL":[57],"spans":[58],"four":[59],"question":[60],"types,":[61],"five":[62],"categories,":[64],"eight":[66],"structural":[67],"archetypes.Evaluations":[68],"state-of-the-art":[70],"models":[71],"reveal":[72],"substantial":[73],"gaps,":[74],"especially":[75],"visual":[77],"grounding,":[78],"spatial":[79],"alignment,":[80],"multi-step":[82],"inference,":[83],"20-40%":[85],"performance":[86],"drops":[87],"relative":[88],"to":[89],"existing":[90],"benchmarks.These":[91],"results":[92],"highlight":[93],"the":[94,123],"need":[95],"architectures":[97],"that":[98,121],"more":[99],"tightly":[100],"fuse":[101],"vision":[102],"structure":[105],"support":[107],"explicit":[108],"numeric/logical":[109],"operations.MMTABREAL":[110],"released":[112],"only,":[115],"providing":[116],"rigorous,":[118],"reproducible":[119],"testbed":[120],"reflects":[122],"linguistic,":[124],"structural,":[125],"complexity":[128],"tables.Code":[132],"data":[134],"available":[136],"at":[137]},"counts_by_year":[],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2025-10-10T00:00:00"}