{"id":"https://openalex.org/W4416034101","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1083","title":"MTabVQA: Evaluating Multi-Tabular Reasoning of Language Models in Visual Space","display_name":"MTabVQA: Evaluating Multi-Tabular Reasoning of Language Models in Visual Space","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034101","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1083"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1083","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1083","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1083.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1083.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112805247","display_name":"Anshul Singh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anshul Singh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021287757","display_name":"Chris Biemann","orcid":"https://orcid.org/0000-0002-8449-9624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chris Biemann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5119204153","display_name":"Jan Strich","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Strich","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28853084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19866","last_page":"19891"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9620000123977661,"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":0.9620000123977661,"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/T10799","display_name":"Data Visualization and Analytics","score":0.006200000178068876,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.0044999998062849045,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/visual-language","display_name":"Visual language","score":0.46239998936653137},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.42879998683929443},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3785000145435333},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3709000051021576},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.32350000739097595},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.3172000050544739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6365000009536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5490000247955322},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46309998631477356},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.46239998936653137},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26269999146461487},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2581000030040741}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1083","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1083","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1083.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1083","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1083","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1083.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320323381","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034101.pdf","grobid_xml":"https://content.openalex.org/works/W4416034101.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"have":[3],"demonstrated":[4],"remarkable":[5],"capabilities":[6],"in":[7,17,34],"interpreting":[8],"visual":[9,79,90,157],"layouts":[10],"and":[11,22,41,72,138,160],"text.However,":[12],"a":[13,31,54,83,141],"significant":[14,122],"challenge":[15],"remains":[16],"their":[18,154],"ability":[19,62],"to":[20,63,93,129],"interpret":[21],"reason":[23],"robustly":[24],"over":[25],"multi-tabular":[26,89,158],"data":[27,51],"presented":[28],"as":[29,38],"images,":[30,67],"common":[32],"occurrence":[33],"real-world":[35],"scenarios":[36],"such":[37],"web":[39],"pages":[40],"digital":[42],"documents.Existing":[43],"benchmarks":[44],"typically":[45],"address":[46],"single":[47],"tables":[48],"or":[49],"non-visual":[50],"(text/structured).This":[52],"leaves":[53],"critical":[55],"gap:":[56],"they":[57],"do":[58],"not":[59],"assess":[60],"the":[61,77,131],"parse":[64],"diverse":[65],"table":[66,110],"correlate":[68],"information":[69],"across":[70,106],"them,":[71],"perform":[73],"multi-hop":[74,104],"reasoning":[75,105,133],"on":[76,119,156],"combined":[78],"data.We":[80],"introduce":[81],"MTab-VQA,":[82],"novel":[84],"benchmark":[85,114],"specifically":[86],"designed":[87],"for":[88,116],"question":[91],"answering":[92],"bridge":[94],"this":[95],"gap.MTabVQA":[96],"comprises":[97],"3,745":[98],"complex":[99],"question-answer":[100],"pairs":[101],"that":[102,147],"necessitate":[103],"several":[107],"visually":[108],"rendered":[109],"images.We":[111],"provide":[112],"extensive":[113],"results":[115],"state-of-the-art":[117],"VLMs":[118,149],"MTabVQA,":[120],"revealing":[121],"performance":[123,155],"limitations.We":[124],"further":[125],"investigate":[126],"posttraining":[127],"techniques":[128],"enhance":[130],"multitabular":[132],"abilities":[134],"of":[135],"vision-language":[136],"models":[137],"release":[139],"MTabVQA-Instruct,":[140],"large-scale":[142],"instruction-tuning":[143],"dataset.Our":[144],"experiments":[145],"show":[146],"fine-tuning":[148],"with":[150],"MTabVQA-Instruct":[151],"substantially":[152],"improves":[153],"reasoning.Code":[159],"dataset":[161],"are":[162],"available":[163],"online":[164],"1":[165],".":[166]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}