{"id":"https://openalex.org/W4415590758","doi":"https://doi.org/10.1007/s13222-025-00513-9","title":"Towards Complex Table Question Answering Over Tabular Data Lakes (Extended Version)","display_name":"Towards Complex Table Question Answering Over Tabular Data Lakes (Extended Version)","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W4415590758","doi":"https://doi.org/10.1007/s13222-025-00513-9"},"language":"en","primary_location":{"id":"doi:10.1007/s13222-025-00513-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13222-025-00513-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13222-025-00513-9.pdf","source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s13222-025-00513-9.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120151399","display_name":"Daniela Risis","orcid":"https://orcid.org/0009-0004-8220-3051"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Daniela Risis","raw_affiliation_strings":["Data and AI Systems, Technical University of Darmstadt, Darmstadt, Germany","SAIDE, DFKI, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Data and AI Systems, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"SAIDE, DFKI, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001221750","display_name":"Jan-Micha Bodensohn","orcid":"https://orcid.org/0000-0003-4884-0300"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan-Micha Bodensohn","raw_affiliation_strings":["Data and AI Systems, Technical University of Darmstadt, Darmstadt, Germany","SAIDE, DFKI, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Data and AI Systems, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"SAIDE, DFKI, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101453287","display_name":"Matthias Urban","orcid":"https://orcid.org/0000-0002-7418-6181"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Urban","raw_affiliation_strings":["Data and AI Systems, Technical University of Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Data and AI Systems, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073504200","display_name":"Carsten Binnig","orcid":"https://orcid.org/0000-0002-2744-7836"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Carsten Binnig","raw_affiliation_strings":["Data and AI Systems, Technical University of Darmstadt, Darmstadt, Germany","SAIDE, DFKI, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Data and AI Systems, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"SAIDE, DFKI, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5120151399"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":{"value":2380,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2380,"currency":"EUR","value_usd":2890},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35474989,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"3","first_page":"145","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9993000030517578,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9926999807357788,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9922000169754028,"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":0.7368000149726868},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7221999764442444},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.6617000102996826},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.4611000120639801},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45509999990463257},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.45159998536109924},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41940000653266907},{"id":"https://openalex.org/keywords/zoom","display_name":"Zoom","score":0.36890000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8162000179290771},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.7368000149726868},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7221999764442444},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6617000102996826},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6468999981880188},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.4611000120639801},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41940000653266907},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.36890000104904175},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3206000030040741},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C44083865","wikidata":"https://www.wikidata.org/wiki/Q3853443","display_name":"Mean reciprocal rank","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28189998865127563},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.26649999618530273},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.265500009059906},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s13222-025-00513-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13222-025-00513-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13222-025-00513-9.pdf","source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:159628","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/view/person/Risis=3ADaniela=3A=3A.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"}],"best_oa_location":{"id":"doi:10.1007/s13222-025-00513-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13222-025-00513-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13222-025-00513-9.pdf","source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3336244616","display_name":null,"funder_award_id":"NHR2021HE","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G5516277521","display_name":null,"funder_award_id":"Kapitel 1502, F\u00f6rderprodukt 19 NHR4CES","funder_id":"https://openalex.org/F4320321961","funder_display_name":"Hessisches Ministerium f\u00fcr Wissenschaft und Kunst"},{"id":"https://openalex.org/G574884202","display_name":null,"funder_award_id":"LOEWE Spitzenprofessur","funder_id":"https://openalex.org/F4320321961","funder_display_name":"Hessisches Ministerium f\u00fcr Wissenschaft und Kunst"},{"id":"https://openalex.org/G618970192","display_name":null,"funder_award_id":"3AI \u2013 The Third Wave of Artificial Intelligence","funder_id":"https://openalex.org/F4320321961","funder_display_name":"Hessisches Ministerium f\u00fcr Wissenschaft und Kunst"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320321961","display_name":"Hessisches Ministerium f\u00fcr Wissenschaft und Kunst","ror":"https://ror.org/00zd5gr55"},{"id":"https://openalex.org/F4320323384","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4415590758.pdf"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2145618437","https://openalex.org/W3102659883","https://openalex.org/W3167748596","https://openalex.org/W3174481949","https://openalex.org/W4281395820","https://openalex.org/W4383605243","https://openalex.org/W4385570342","https://openalex.org/W4385570795","https://openalex.org/W4396988354","https://openalex.org/W4400529822","https://openalex.org/W4402671917","https://openalex.org/W4402704461","https://openalex.org/W4405205161","https://openalex.org/W6887884796"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Natural":[1],"Language":[2,74],"Interfaces":[3],"for":[4],"Databases":[5],"(NLIDBs)":[6],"offer":[7,188],"an":[8,93],"interesting":[9],"alternative":[10],"to":[11,17,25,92,95,169,203],"SQL":[12],"since":[13,48],"they":[14,21],"empower":[15],"non-experts":[16],"query":[18,198],"data.":[19],"However,":[20],"require":[22],"this":[23,101,141],"data":[24,34,55,85,118,210],"be":[26],"integrated":[27],"into":[28,61],"a":[29,62,84,145],"database":[30],"schema,":[31],"causing":[32],"high":[33],"engineering":[35],"and":[36,87,158],"integration":[37],"overheads.":[38],"As":[39],"such,":[40],"Open":[41],"Table":[42],"Question":[43],"Answering":[44],"(OTQA)":[45],"is":[46],"promising":[47],"it":[49],"allows":[50],"directly":[51],"querying":[52,184],"tables":[53,79],"in":[54],"lakes":[56],"without":[57],"first":[58,81],"incorporating":[59],"them":[60],"relational":[63],"schema.":[64],"Many":[65],"recent":[66],"OTQA":[67],"approaches":[68],"combine":[69],"retrieval-augmented":[70],"generation":[71,125],"with":[72,109],"Large":[73],"Models":[75],"(LLMs),":[76],"where":[77],"relevant":[78],"are":[80],"retrieved":[82],"from":[83,181],"lake":[86],"then":[88],"used":[89],"as":[90],"input":[91],"LLM":[94],"answer":[96,113,124,170],"the":[97,123,129,135,182,197],"user":[98],"query.":[99],"In":[100],"paper,":[102],"we":[103,143],"systematically":[104],"analyze":[105],"how":[106],"LLMs":[107,165,202],"paired":[108],"table":[110],"retrievers":[111],"can":[112],"queries":[114],"over":[115,208],"private":[116],"tabular":[117,137,209],"lakes.":[119,211],"We":[120],"find":[121],"that":[122,186],"often":[126,166],"fails":[127],"because":[128],"retrieval":[130,148,156],"step":[131],"does":[132],"not":[133],"provide":[134],"required":[136],"context.":[138],"To":[139],"overcome":[140],"issue,":[142],"propose":[144],"novel":[146],"LLM-based":[147],"approach":[149],"called":[150],"Zoom":[151],"retrieval,":[152],"which":[153],"effectively":[154],"boosts":[155],"accuracies":[157],"thereby":[159],"improves":[160],"question":[161,206],"answering":[162,207],"results.":[163],"Nevertheless,":[164],"still":[167],"fail":[168],"even":[171],"simple":[172],"extraction":[173],"queries,":[174],"let":[175],"alone":[176],"aggregates,":[177],"thus":[178],"remaining":[179],"far":[180],"rich":[183],"capabilities":[185,200],"NLIDBs":[187],"today.":[189],"Therefore,":[190],"future":[191],"work":[192],"should":[193],"focus":[194],"on":[195],"improving":[196],"execution":[199],"of":[201],"enable":[204],"complex":[205]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-28T00:00:00"}