{"id":"https://openalex.org/W7128499114","doi":"https://doi.org/10.48550/arxiv.2602.07642","title":"Efficient Table Retrieval and Understanding with Multimodal Large Language Models","display_name":"Efficient Table Retrieval and Understanding with Multimodal Large Language Models","publication_year":2026,"publication_date":"2026-02-07","ids":{"openalex":"https://openalex.org/W7128499114","doi":"https://doi.org/10.48550/arxiv.2602.07642"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.07642","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125537306","display_name":"Zhuoyan Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Zhuoyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125581650","display_name":"Haoyang Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Haoyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041872681","display_name":"Boran Han","orcid":"https://orcid.org/0000-0001-9567-7062"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Boran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060769750","display_name":"Bonan Min","orcid":"https://orcid.org/0000-0002-6114-8418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min, Bonan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125545906","display_name":"Bernie Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Bernie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125481674","display_name":"Cuixiong Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Cuixiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125516750","display_name":"Shuai Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shuai","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16946253,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.8758000135421753,"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":0.8758000135421753,"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/T11719","display_name":"Data Quality and Management","score":0.023900000378489494,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.01080000028014183,"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/table","display_name":"Table (database)","score":0.8203999996185303},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4758000075817108},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.47369998693466187},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.426800012588501},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4034999907016754},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.3788999915122986},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3165000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8495000004768372},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.8203999996185303},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5949000120162964},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4758000075817108},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.47369998693466187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4641000032424927},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40459999442100525},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38519999384880066},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3343999981880188},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C2780977526","wikidata":"https://www.wikidata.org/wiki/Q42417149","display_name":"Data exploration","level":3,"score":0.2784000039100647},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.07642","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},{"id":"doi:10.48550/arxiv.2602.07642","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.07642","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":"pmh:doi:10.48550/arxiv.2602.07642","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"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":{"Tabular":[0],"data":[1],"is":[2,62],"frequently":[3],"captured":[4],"in":[5,44,53,173,178],"image":[6],"form":[7],"across":[8,155],"a":[9,66,91,144,182],"wide":[10],"range":[11],"of":[12,102,124],"real-world":[13,186],"scenarios":[14],"such":[15],"as":[16,33],"financial":[17],"reports,":[18],"handwritten":[19],"records,":[20],"and":[21,38,72,127,151,176],"document":[22],"scans.":[23],"These":[24],"visual":[25,39],"representations":[26],"pose":[27],"unique":[28,160],"challenges":[29],"for":[30,137,185],"machine":[31],"understanding,":[32,55],"they":[34,56],"combine":[35],"both":[36],"structural":[37],"complexities.":[40],"While":[41],"recent":[42],"advances":[43],"Multimodal":[45],"Large":[46],"Language":[47],"Models":[48],"(MLLMs)":[49],"show":[50],"promising":[51],"results":[52],"table":[54,61,103,187],"typically":[57],"assume":[58],"the":[59,134],"relevant":[60,75],"readily":[63],"available.":[64],"However,":[65],"more":[67],"practical":[68,183],"scenario":[69],"involves":[70],"identifying":[71],"reasoning":[73],"over":[74,99,133],"tables":[76,110,136],"from":[77],"large-scale":[78],"collections":[79,101],"to":[80,96,120,131],"answer":[81,97,138,179],"user":[82],"queries.":[83],"To":[84],"address":[85],"this":[86],"gap,":[87],"we":[88,162],"propose":[89],"TabRAG,":[90],"framework":[92,166],"that":[93,164],"enables":[94],"MLLMs":[95,119,130],"queries":[98],"large":[100],"images.":[104],"Our":[105],"approach":[106],"first":[107],"retrieves":[108],"candidate":[109],"using":[111],"jointly":[112],"trained":[113],"visual-text":[114],"foundation":[115],"models,":[116],"then":[117],"leverages":[118],"perform":[121],"fine-grained":[122],"reranking":[123],"these":[125],"candidates,":[126],"finally":[128],"employs":[129],"reason":[132],"selected":[135],"generation.":[139],"Through":[140],"extensive":[141],"experiments":[142],"on":[143],"newly":[145],"constructed":[146],"dataset":[147],"comprising":[148],"88,161":[149],"training":[150],"9,819":[152],"testing":[153],"samples":[154],"8":[156],"benchmarks":[157],"with":[158],"48,504":[159],"tables,":[161],"demonstrate":[163],"our":[165],"significantly":[167],"outperforms":[168],"existing":[169],"methods":[170],"by":[171],"7.0%":[172],"retrieval":[174],"recall":[175],"6.1%":[177],"accuracy,":[180],"offering":[181],"solution":[184],"understanding":[188],"tasks.":[189]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-02-11T00:00:00"}