{"id":"https://openalex.org/W4399452982","doi":"https://doi.org/10.1145/3661304.3661901","title":"A Benchmark to Understand the Role of Knowledge Graphs on Large Language Model's Accuracy for Question Answering on Enterprise SQL Databases","display_name":"A Benchmark to Understand the Role of Knowledge Graphs on Large Language Model's Accuracy for Question Answering on Enterprise SQL Databases","publication_year":2024,"publication_date":"2024-06-05","ids":{"openalex":"https://openalex.org/W4399452982","doi":"https://doi.org/10.1145/3661304.3661901"},"language":"en","primary_location":{"id":"doi:10.1145/3661304.3661901","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3661304.3661901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint Workshop on Graph Data Management Experiences & Systems (GRADES) and Network Data Analytics (NDA)","raw_type":"proceedings-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/A5014287041","display_name":"Juan Sequeda","orcid":"https://orcid.org/0000-0003-3112-9299"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan Sequeda","raw_affiliation_strings":["data.world, Austin, USA"],"raw_orcid":"https://orcid.org/0000-0003-3112-9299","affiliations":[{"raw_affiliation_string":"data.world, Austin, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103009679","display_name":"Dean Allemang","orcid":"https://orcid.org/0009-0009-4065-5726"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dean Allemang","raw_affiliation_strings":["data.world, Austin, USA"],"raw_orcid":"https://orcid.org/0009-0009-4065-5726","affiliations":[{"raw_affiliation_string":"data.world, Austin, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043325606","display_name":"Bryon Jacob","orcid":"https://orcid.org/0000-0003-0470-9300"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bryon Jacob","raw_affiliation_strings":["data.world, Austin, USA"],"raw_orcid":"https://orcid.org/0000-0003-0470-9300","affiliations":[{"raw_affiliation_string":"data.world, Austin, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.1272,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.97891711,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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":0.9980000257492065,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9959999918937683,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9905999898910522,"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/computer-science","display_name":"Computer science","score":0.7918704152107239},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.7466541528701782},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7081980109214783},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6242552995681763},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4890531003475189},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4333397150039673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3821903169155121},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38034260272979736},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3716139793395996}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918704152107239},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.7466541528701782},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7081980109214783},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6242552995681763},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4890531003475189},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4333397150039673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3821903169155121},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38034260272979736},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3716139793395996},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3661304.3661901","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3661304.3661901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint Workshop on Graph Data Management Experiences & Systems (GRADES) and Network Data Analytics (NDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1453946243","https://openalex.org/W1700952868","https://openalex.org/W1823168806","https://openalex.org/W1979263599","https://openalex.org/W2002947720","https://openalex.org/W2035032881","https://openalex.org/W2043794661","https://openalex.org/W2269738476","https://openalex.org/W2607303097","https://openalex.org/W2762513422","https://openalex.org/W2798663534","https://openalex.org/W2899575547","https://openalex.org/W3104055253","https://openalex.org/W3197731571","https://openalex.org/W4230471358"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2387743295","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574"],"abstract_inverted_index":{"Enterprise":[0],"applications":[1],"of":[2,36,47,71,79,90,114,154,171],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"hold":[7],"promise":[8],"for":[9,184],"question":[10,54,73,140,187],"answering":[11,55,74,141,188],"on":[12,148],"enterprise":[13,26,42,80,105,115,173],"SQL":[14,83,106,149,174],"databases.":[15],"However,":[16],"the":[17,34,45,69,77,88,109,172],"extent":[18],"to":[19,25,41,51,67,119,160],"which":[20],"LLMs":[21],"can":[22],"accurately":[23],"respond":[24],"questions":[27,81,163],"in":[28,76,93,108,178],"such":[29],"databases":[30],"remains":[31],"unclear,":[32],"given":[33],"absence":[35],"suitable":[37],"Text-to-SQL":[38],"benchmarks":[39],"tailored":[40],"settings.":[43],"Additionally,":[44],"potential":[46],"Knowledge":[48,168,179],"Graphs":[49],"(KGs)":[50],"enhance":[52],"LLM-based":[53],"by":[56],"providing":[57],"business":[58],"context":[59,78],"is":[60],"not":[61],"well":[62],"understood.":[63],"This":[64],"study":[65],"aims":[66],"evaluate":[68],"accuracy":[70,153,158,183],"LLM-powered":[72],"systems":[75],"and":[82,121,128],"databases,":[84,150],"while":[85],"also":[86],"exploring":[87],"role":[89],"knowledge":[91,133],"graphs":[92],"improving":[94],"accuracy.":[95],"To":[96],"achieve":[97],"this,":[98],"we":[99],"introduce":[100],"a":[101,112,122,132,167],"benchmark":[102],"comprising":[103],"an":[104,126,152],"schema":[107],"insurance":[110],"domain,":[111],"range":[113],"queries":[116],"encompassing":[117],"reporting":[118],"metrics,":[120],"contextual":[123],"layer":[124],"incorporating":[125],"ontology":[127],"mappings":[129],"that":[130,139],"define":[131],"graph.":[134],"Our":[135],"primary":[136],"finding":[137],"reveals":[138],"using":[142],"GPT-4,":[143],"with":[144],"zero-shot":[145],"prompts":[146],"directly":[147],"achieves":[151],"16%.":[155],"Notably,":[156],"this":[157],"increases":[159],"54%":[161],"when":[162],"are":[164],"posed":[165],"over":[166],"Graph":[169,180],"representation":[170],"database.":[175],"Therefore,":[176],"investing":[177],"provides":[181],"higher":[182],"LLM":[185],"powered":[186],"systems.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":12}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}