{"id":"https://openalex.org/W7163994637","doi":"https://doi.org/10.48550/arxiv.2606.09578","title":"TABVERSE: Benchmarking Cross-Format Table Understanding in LLMs and VLMs","display_name":"TABVERSE: Benchmarking Cross-Format Table Understanding in LLMs and VLMs","publication_year":2026,"publication_date":"2026-06-08","ids":{"openalex":"https://openalex.org/W7163994637","doi":"https://doi.org/10.48550/arxiv.2606.09578"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.09578","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09578","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,"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.2606.09578","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104157672","display_name":"Momina Ahsan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahsan, Momina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026976984","display_name":"Sarfraz Ahmad","orcid":"https://orcid.org/0000-0003-0059-477X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmad, Sarfraz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045458136","display_name":"Ming Shan Hee","orcid":"https://orcid.org/0000-0002-6328-5889"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hee, Ming Shan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138274898","display_name":"Roy Ka-Wei Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Roy Ka-Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138218253","display_name":"Preslav Nakov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nakov, Preslav","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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.35350000858306885,"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":0.35350000858306885,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.12449999898672104,"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":0.0989999994635582,"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","display_name":"Table (database)","score":0.8899000287055969},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.722599983215332},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5648999810218811},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5425000190734863},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.5340999960899353},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4964999854564667},{"id":"https://openalex.org/keywords/decision-table","display_name":"Decision table","score":0.40369999408721924}],"concepts":[{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.8899000287055969},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.722599983215332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6470000147819519},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5648999810218811},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5425000190734863},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.5340999960899353},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4964999854564667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4146000146865845},{"id":"https://openalex.org/C172967692","wikidata":"https://www.wikidata.org/wiki/Q747762","display_name":"Decision table","level":3,"score":0.40369999408721924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39570000767707825},{"id":"https://openalex.org/C68476402","wikidata":"https://www.wikidata.org/wiki/Q1456936","display_name":"Table of contents","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3483999967575073},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31130000948905945},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29429998993873596},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.09578","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09578","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,"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.2606.09578","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09578","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,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2,6,133],"(LLMs)":[3],"and":[4,39,53,82,88,107,119,155,169],"Vision-Language":[5],"(VLMs)":[7],"are":[8],"increasingly":[9],"evaluated":[10],"on":[11,151],"table":[12,19,27,70,76,101,131,180,188],"reasoning":[13],"tasks,":[14],"but":[15,144],"the":[16,25,74,145,152,160],"role":[17],"of":[18,96,147],"representation":[20,62,97,127,181],"remains":[21],"under-explored.":[22],"In":[23],"practice,":[24],"same":[26,75],"content":[28,77,102],"may":[29],"appear":[30],"in":[31,186],"different":[32],"structural":[33,80,167],"formats,":[34],"such":[35],"as":[36,42],"HTML,":[37],"Markdown,":[38],"LaTeX,":[40],"or":[41],"rendered":[43,83,142],"images.":[44],"However,":[45],"existing":[46],"evaluations":[47],"often":[48,159],"let":[49],"content,":[50],"format,":[51,164],"layout,":[52],"modality":[54],"vary":[55],"together,":[56],"making":[57],"it":[58],"difficult":[59],"to":[60],"isolate":[61],"effects.":[63],"We":[64,104],"introduce":[65],"TABVERSE,":[66],"a":[67,183],"controlled":[68],"multimodal":[69],"benchmark":[71],"that":[72,126,179],"aligns":[73],"across":[78,109],"multiple":[79],"formats":[81],"images,":[84,143],"with":[85,137,141],"question":[86],"category":[87],"difficulty":[89],"tags.":[90],"This":[91],"design":[92],"enables":[93],"systematic":[94],"evaluation":[95],"effects":[98],"while":[99,165],"holding":[100],"fixed.":[103],"evaluate":[105],"LLMs":[106],"VLMs":[108],"three":[110],"tasks:":[111],"Question":[112],"Answering":[113],"(QA),":[114],"Structural":[115],"Understanding":[116],"Capability":[117],"(SUC),":[118],"Structure":[120],"Reconstruction":[121],"(SR).":[122],"Our":[123],"results":[124],"show":[125,178],"choice":[128],"substantially":[129],"affects":[130],"understanding.":[132],"generally":[134],"perform":[135],"better":[136],"structured":[138],"text":[139,163],"than":[140],"size":[146],"this":[148],"gap":[149],"depends":[150],"task,":[153],"model,":[154],"format.":[156],"HTML":[157],"is":[158,182],"most":[161],"robust":[162],"row-sensitive":[166],"tasks":[168],"syntactically":[170],"usable":[171],"LaTeX":[172],"reconstruction":[173],"remain":[174],"challenging.":[175],"These":[176],"findings":[177],"key":[184],"factor":[185],"reliable":[187],"evaluation.":[189]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-10T00:00:00"}