{"id":"https://openalex.org/W4403577485","doi":"https://doi.org/10.1145/3627673.3679713","title":"Aligning Large Language Models to a Domain-specific Graph Database for NL2GQL","display_name":"Aligning Large Language Models to a Domain-specific Graph Database for NL2GQL","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403577485","doi":"https://doi.org/10.1145/3627673.3679713"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679713","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679713","pdf_url":null,"source":null,"license":null,"license_id":null,"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":"conference-paper","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":null,"display_name":"Yuanyuan Liang","orcid":"https://orcid.org/0009-0005-3424-1042"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Liang","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-3424-1042","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Keren Tan","orcid":"https://orcid.org/0009-0007-0898-6264"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keren Tan","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-0898-6264","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013015812","display_name":"Tingyu Xie","orcid":"https://orcid.org/0000-0003-2361-8842"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingyu Xie","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2361-8842","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061251283","display_name":"Wenbiao Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbiao Tao","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-5978-094X","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Siyuan Wang","orcid":"https://orcid.org/0009-0008-9459-6162"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Wang","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-9459-6162","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090588589","display_name":"Yunshi Lan","orcid":"https://orcid.org/0000-0002-0192-8498"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunshi Lan","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0192-8498","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089931216","display_name":"Weining Qian","orcid":"https://orcid.org/0000-0002-4132-8630"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weining Qian","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4132-8630","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1367","last_page":"1377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.8164939880371094},{"id":"https://openalex.org/keywords/graph-database","display_name":"Graph database","score":0.5666991472244263},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.49041271209716797},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4551718831062317},{"id":"https://openalex.org/keywords/domain-specific-language","display_name":"Domain-specific language","score":0.45157235860824585},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3821164667606354},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.340467631816864},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3200143575668335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8164939880371094},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.5666991472244263},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.49041271209716797},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4551718831062317},{"id":"https://openalex.org/C135257023","wikidata":"https://www.wikidata.org/wiki/Q691358","display_name":"Domain-specific language","level":2,"score":0.45157235860824585},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3821164667606354},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.340467631816864},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3200143575668335}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679713","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679713","pdf_url":null,"source":null,"license":null,"license_id":null,"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":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1969483458","https://openalex.org/W2981117684","https://openalex.org/W3034862985","https://openalex.org/W3100058503","https://openalex.org/W3156366114","https://openalex.org/W4221143046","https://openalex.org/W4229878270","https://openalex.org/W4280534475","https://openalex.org/W4284698238","https://openalex.org/W4306317757","https://openalex.org/W4312334053","https://openalex.org/W4381326864","https://openalex.org/W4381599258","https://openalex.org/W4382246105","https://openalex.org/W4385570710","https://openalex.org/W4387994678","https://openalex.org/W4388488349","https://openalex.org/W4389523875","https://openalex.org/W4390692489","https://openalex.org/W4391039286","https://openalex.org/W4393156804","https://openalex.org/W4396571402","https://openalex.org/W4404780967"],"related_works":["https://openalex.org/W2161550557","https://openalex.org/W2148282566","https://openalex.org/W4387796988","https://openalex.org/W2065949834","https://openalex.org/W2150010249","https://openalex.org/W2303430181","https://openalex.org/W2071356121","https://openalex.org/W2924405342","https://openalex.org/W3115442681","https://openalex.org/W2391000461"],"abstract_inverted_index":{"Graph":[0,26],"Databases":[1],"(Graph":[2],"DB)":[3],"find":[4,143],"extensive":[5],"application":[6],"across":[7],"diverse":[8],"domains":[9],"such":[10],"as":[11,32,163],"finance,":[12],"social":[13],"networks,":[14],"and":[15,41,111,122,137,183,188,207,213,215,223],"medicine.":[16],"Yet,":[17],"the":[18,25,62,72,85,107,127,138,144,164,181],"translation":[19],"of":[20,64,74,146,200,205],"Natural":[21],"Language":[22,28,51],"(NL)":[23],"into":[24],"Query":[27],"(GQL),":[29],"referred":[30],"to":[31,38,48,54,68,81,101,130,159],"NL2GQL,":[33],"poses":[34],"significant":[35],"challenges":[36],"owing":[37],"its":[39],"intricate":[40],"specialized":[42],"nature.":[43],"Some":[44],"approaches":[45],"have":[46],"sought":[47],"utilize":[49],"Large":[50],"Models":[52],"(LLMs)":[53],"address":[55],"analogous":[56],"tasks":[57,66],"like":[58],"text2SQL.":[59],"Nonetheless,":[60],"in":[61,149,180],"realm":[63],"NL2GQL":[65],"tailored":[67],"a":[69,94,157,198],"particular":[70],"domain,":[71],"absence":[73],"domain-specific":[75],"NL-GQL":[76,103],"data":[77,104,129],"pairs":[78],"adds":[79],"complexity":[80],"aligning":[82],"LLMs":[83,136],"with":[84,203],"graph":[86,109,139,178],"DB.":[87,140],"To":[88],"tackle":[89],"this":[90],"challenge,":[91],"we":[92,98,125,142,155],"present":[93],"well-defined":[95],"pipeline.":[96],"Initially,":[97],"use":[99],"ChatGPT":[100],"generate":[102],"pairs,":[105],"leveraging":[106],"provided":[108],"DB":[110],"two":[112,172],"mutual":[113],"verification":[114],"self-instruct":[115],"methods":[116],"which":[117],"ensure":[118],"consistency":[119],"between":[120,135],"NL":[121],"GQL.":[123],"Subsequently,":[124],"employ":[126],"generated":[128],"fine-tune":[131],"LLMs,":[132],"ensuring":[133],"alignment":[134],"Moreover,":[141],"importance":[145],"relevant":[147,161],"schema":[148,162],"efficiently":[150],"generating":[151],"accurate":[152],"GQLs.":[153],"Thus,":[154],"introduce":[156],"method":[158,170],"extract":[160],"input":[165],"context.":[166],"We":[167],"evaluate":[168],"our":[169,194],"using":[171],"carefully":[173],"constructed":[174],"datasets":[175],"derived":[176],"from":[177],"DBs":[179],"finance":[182],"medicine":[184],"domains,":[185],"named":[186],"FinGQL":[187,222],"MediGQL.":[189],"Experimental":[190],"results":[191],"reveal":[192],"that":[193],"approach":[195],"significantly":[196],"outperforms":[197],"set":[199],"baseline":[201],"methods,":[202],"improvements":[204],"5.90":[206],"6.36":[208],"absolute":[209,217],"points":[210,218],"on":[211,219],"EM,":[212],"6.00":[214],"7.09":[216],"EX":[220],"for":[221],"MediGQL,":[224],"respectively":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}