{"id":"https://openalex.org/W4403582620","doi":"https://doi.org/10.1145/3627673.3679932","title":"Generating Cross-model Analytics Workloads Using LLMs","display_name":"Generating Cross-model Analytics Workloads Using LLMs","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403582620","doi":"https://doi.org/10.1145/3627673.3679932"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679932","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679932","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3627673.3679932","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090512931","display_name":"X Zheng","orcid":"https://orcid.org/0000-0002-2617-1647"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiuwen Zheng","raw_affiliation_strings":["University of California, San Diego, La Jolla, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, La Jolla, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089490605","display_name":"Arun Kumar","orcid":"https://orcid.org/0009-0007-5036-2631"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arun Kumar","raw_affiliation_strings":["University of California, San Diego, La Jolla, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, La Jolla, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057846313","display_name":"Amarnath Gupta","orcid":"https://orcid.org/0000-0003-0897-120X"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amarnath Gupta","raw_affiliation_strings":["University of California, San Diego, La Jolla, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, La Jolla, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090512931"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16245662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4303","last_page":"4307"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9912999868392944,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9912999868392944,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9894999861717224,"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/T11719","display_name":"Data Quality and Management","score":0.9833999872207642,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6596439480781555},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6163057088851929},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4363752603530884}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6596439480781555},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6163057088851929},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4363752603530884}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679932","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679932","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3627673.3679932","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679932","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2292449291","https://openalex.org/W2299839756","https://openalex.org/W2396309311","https://openalex.org/W2753392522","https://openalex.org/W2793682084","https://openalex.org/W2889140904","https://openalex.org/W2891512841","https://openalex.org/W2915055379","https://openalex.org/W3083533005","https://openalex.org/W3084489972","https://openalex.org/W3098039048","https://openalex.org/W3155753090","https://openalex.org/W3175479149","https://openalex.org/W4366492480"],"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/W4390482427"],"abstract_inverted_index":{"Data":[0],"analytics":[1,147],"applications":[2],"today":[3],"often":[4],"require":[5,80],"processing":[6],"heterogeneous":[7],"data":[8,11,28,48],"from":[9,55],"different":[10,157],"models,":[12,29],"including":[13],"relational,":[14],"graph,":[15],"and":[16,83,92,140,163,177,182,191,216],"text":[17],"data,":[18,32,142,215],"for":[19,26,36,46,115],"more":[20],"holistic":[21],"analytics.":[22,49],"While":[23],"query":[24,44,51,63,87,95,136,171,217],"optimization":[25,45,52,64],"single":[27],"especially":[30],"relational":[31,67,139],"has":[33],"been":[34],"studied":[35],"decades,":[37],"there":[38,103],"is":[39],"surprisingly":[40],"little":[41],"work":[42,61],"on":[43],"cross-model":[47,109,206],"Cross-model":[50],"can":[53],"benefit":[54],"the":[56,66,98,175,189,195,208],"long":[57],"line":[58],"of":[59,86,100,179,194],"prior":[60],"in":[62,65,118,146],"realm,":[68],"wherein":[69],"cost-based":[70],"and/or":[71],"machine":[72],"learning-based":[73],"(ML-based)":[74],"optimizers":[75],"are":[76,104,144],"common.":[77],"Both":[78],"approaches":[79],"a":[81,94,112,126],"large":[82,107,152],"diverse":[84],"set":[85,210],"workloads":[88,137,218],"to":[89,160,169],"measure,":[90],"tune,":[91],"evaluate":[93,174],"optimizer.":[96],"To":[97],"best":[99],"our":[101],"knowledge,":[102],"still":[105],"no":[106],"public":[108],"benchmark":[110],"workloads,":[111],"significant":[113],"obstacle":[114],"systems":[116],"researchers":[117],"this":[119,122,130],"space.":[120],"In":[121],"paper,":[123],"we":[124,200],"take":[125],"step":[127],"toward":[128],"filling":[129],"research":[131],"gap":[132],"by":[133,187],"generating":[134],"new":[135,165],"spanning":[138],"graph":[141],"which":[143],"ubiquitous":[145],"applications.":[148],"Our":[149,212],"approach":[150],"leverages":[151],"language":[153],"models":[154],"(LLMs)":[155],"via":[156],"prompting":[158],"strategies":[159],"generate":[161],"queries":[162],"proposes":[164],"rule-based":[166],"post-processing":[167],"methods":[168],"ensure":[170],"correctness.":[172],"We":[173],"pros":[176],"cons":[178],"each":[180],"strategy":[181],"perform":[183],"an":[184],"in-depth":[185],"analysis":[186],"categorizing":[188],"syntactic":[190],"semantic":[192],"errors":[193],"generated":[196],"queries.":[197],"So":[198],"far,":[199],"have":[201],"produced":[202],"over":[203],"4000":[204],"correct":[205],"queries,":[207],"largest":[209],"ever.":[211],"code,":[213],"prompts,":[214],"will":[219],"all":[220],"be":[221],"released":[222],"publicly.":[223]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}