{"id":"https://openalex.org/W4404181035","doi":"https://doi.org/10.14778/3685800.3685905","title":"Chat2Data: An Interactive Data Analysis System with RAG, Vector Databases and LLMs","display_name":"Chat2Data: An Interactive Data Analysis System with RAG, Vector Databases and LLMs","publication_year":2024,"publication_date":"2024-08-01","ids":{"openalex":"https://openalex.org/W4404181035","doi":"https://doi.org/10.14778/3685800.3685905"},"language":"en","primary_location":{"id":"doi:10.14778/3685800.3685905","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3685800.3685905","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070250000","display_name":"Xinyang Zhao","orcid":"https://orcid.org/0009-0001-3534-1644"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyang Zhao","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056912386","display_name":"Xuanhe Zhou","orcid":"https://orcid.org/0000-0002-2285-7836"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanhe Zhou","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100404163","display_name":"Guoliang Li","orcid":"https://orcid.org/0000-0003-1601-6640"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":8.1158,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.97951567,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"17","issue":"12","first_page":"4481","last_page":"4484"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9861999750137329,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9861999750137329,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.98580002784729,"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"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9746000170707703,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/database","display_name":"Database","score":0.6219448447227478},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5226073861122131},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33058303594589233},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32859551906585693}],"concepts":[{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6219448447227478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5226073861122131},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33058303594589233},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32859551906585693}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3685800.3685905","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3685800.3685905","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W3165814564","https://openalex.org/W4317641620","https://openalex.org/W4381621971","https://openalex.org/W4384918448"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Traditional":[0],"data":[1,39,51,104,193,201],"analysis":[2],"methods":[3],"require":[4],"users":[5,34],"to":[6,14,35,57,73,100,121,127,138,148,160,165,173,179],"write":[7],"programming":[8],"codes":[9,61],"or":[10,60],"issue":[11],"SQL":[12,58],"queries":[13,59],"analyze":[15,102],"the":[16,38,54,103,114,129,132,140,150,153,175,181],"data,":[17],"which":[18],"are":[19],"inconvenient":[20],"for":[21,49,62,77,82,88],"ordinary":[22],"users.":[23],"Large":[24],"language":[25,42],"models":[26],"(LLMs)":[27],"can":[28],"alleviate":[29],"these":[30,93],"limitations":[31],"by":[32],"enabling":[33],"interact":[36],"with":[37,40,105,144,188],"natural":[41,106,198],"(NL),":[43],"e.g.,":[44],"result":[45],"retrieval":[46,194],"and":[47,52,85,152,168,195,197],"summarization":[48],"unstructured":[50,192],"transforming":[53],"NL":[55],"text":[56],"structured":[63,200],"data.":[64],"However,":[65],"existing":[66],"LLMs":[67,145],"have":[68],"three":[69],"limitations:":[70],"hallucination":[71,130],"(due":[72],"lacking":[74],"domain":[75,123],"knowledge":[76,124],"vertical":[78],"domains),":[79],"high":[80],"cost":[81],"LLM":[83],"reasoning,":[84],"low":[86],"accuracy":[87,182],"complicated":[89],"tasks.":[90],"To":[91],"address":[92,128],"problems,":[94],"we":[95],"propose":[96],"a":[97,110,157,162],"prototype,":[98],"Chat2Data,":[99],"interactively":[101],"language.":[107],"Chat2Data":[108,187],"adopts":[109],"three-layer":[111],"method,":[112],"where":[113],"first":[115],"layer":[116,134,155],"uses":[117],"Retrieval-Augmented":[118],"Generation":[119],"(RAG)":[120],"embed":[122],"in":[125,177],"order":[126,178],"problem,":[131],"second":[133],"utilizes":[135],"vector":[136],"databases":[137],"reduce":[139],"number":[141],"of":[142,183],"interactions":[143],"so":[146],"as":[147],"improve":[149,180],"performance,":[151],"third":[154],"designs":[156],"pipeline":[158],"agent":[159],"decompose":[161],"complex":[163],"task":[164],"multiple":[166,170],"subtasks":[167],"use":[169],"round":[171],"reasoning":[172],"generate":[174],"results":[176],"LLMs.":[184],"We":[185],"demonstrate":[186],"two":[189],"real":[190],"scenarios,":[191],"summarization,":[196],"language-based":[199],"analysis.":[202],"The":[203],"online":[204],"demo":[205],"is":[206],"available":[207],"at":[208],"http://vdemo.dbmind.cn.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}