{"id":"https://openalex.org/W4414243320","doi":"https://doi.org/10.14778/3750601.3750679","title":"ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Models","display_name":"ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Models","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4414243320","doi":"https://doi.org/10.14778/3750601.3750679"},"language":"en","primary_location":{"id":"doi:10.14778/3750601.3750679","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3750601.3750679","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":null,"display_name":"Jianxin Yan","orcid":null},"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":true,"raw_author_name":"Jianxin Yan","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056383703","display_name":"Wangze Ni","orcid":"https://orcid.org/0000-0003-1438-1345"},"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":"Wangze Ni","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333516","display_name":"Lei Chen","orcid":"https://orcid.org/0000-0002-8257-5806"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lei Chen","raw_affiliation_strings":["HKUST (GZ) &amp; HKUST, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST (GZ) &amp; HKUST, Guangzhou, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659938","display_name":"Xuemin Lin","orcid":"https://orcid.org/0000-0003-2396-7225"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuemin Lin","raw_affiliation_strings":["Shanghai Jiaotong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiaotong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017961341","display_name":"Peng Cheng","orcid":"https://orcid.org/0000-0002-8058-7985"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Cheng","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100564870","display_name":"Zhan Qin","orcid":null},"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":"Zhan Qin","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000596496","display_name":"Kui Ren","orcid":"https://orcid.org/0000-0003-3441-6277"},"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":"Kui Ren","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":1.9269,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89394914,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"18","issue":"12","first_page":"5391","last_page":"5394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9984999895095825,"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":0.9984999895095825,"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/T11719","display_name":"Data Quality and Management","score":0.9962000250816345,"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":0.9864000082015991,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5324000120162964},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5260000228881836},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4997999966144562},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.48559999465942383},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4431999921798706},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.42820000648498535},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3799999952316284},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.3799000084400177}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8827999830245972},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5324000120162964},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5260000228881836},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.48559999465942383},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.42820000648498535},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41429999470710754},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.374099999666214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34610000252723694},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.3246000111103058},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.2913999855518341},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.2732999920845032}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3750601.3750679","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3750601.3750679","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"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-169075","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-169075","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2093698835","https://openalex.org/W4389523830"],"related_works":[],"abstract_inverted_index":{"Semantic":[0],"caching":[1,54],"significantly":[2],"reduces":[3],"computational":[4,123],"costs":[5],"and":[6,11,78,82,102],"improves":[7,100],"efficiency":[8],"by":[9],"storing":[10],"reusing":[12],"large":[13],"language":[14],"model":[15],"(LLM)":[16],"responses.":[17],"However,":[18],"existing":[19,106],"systems":[20],"rely":[21],"primarily":[22],"on":[23,70],"matching":[24],"individual":[25],"queries,":[26],"lacking":[27],"awareness":[28],"of":[29,94],"multi-turn":[30,57],"dialogue":[31,84],"contexts,":[32],"which":[33],"leads":[34],"to":[35,74,105],"incorrect":[36],"cache":[37],"hits":[38],"when":[39],"similar":[40],"queries":[41],"appear":[42],"in":[43],"different":[44],"conversational":[45,128],"settings.":[46],"This":[47],"demonstration":[48],"introduces":[49],"ContextCache,":[50],"a":[51,61],"context-aware":[52],"semantic":[53],"system":[55],"for":[56,89,126],"dialogues.":[58],"ContextCache":[59,99],"employs":[60],"two-stage":[62],"retrieval":[63,69],"architecture":[64],"that":[65,98],"first":[66],"executes":[67],"vector-based":[68],"the":[71],"current":[72,81],"query":[73],"identify":[75],"potential":[76],"matches":[77],"then":[79],"integrates":[80],"historical":[83],"representations":[85],"through":[86],"self-attention":[87],"mechanisms":[88],"precise":[90],"contextual":[91],"matching.":[92],"Evaluation":[93],"real-world":[95],"conversations":[96],"shows":[97],"precision":[101],"recall":[103],"compared":[104],"methods.":[107],"Additionally,":[108],"cached":[109],"responses":[110],"exhibit":[111],"approximately":[112],"10":[113],"times":[114],"lower":[115],"latency":[116],"than":[117],"direct":[118],"LLM":[119,127],"invocation,":[120],"enabling":[121],"significant":[122],"cost":[124],"reductions":[125],"applications.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}
