{"id":"https://openalex.org/W4416854088","doi":"https://doi.org/10.1109/infocom59046.2026.11571467","title":"Semantic Caching for Low-Cost LLM Serving: From Offline Learning to Online Adaptation","display_name":"Semantic Caching for Low-Cost LLM Serving: From Offline Learning to Online Adaptation","publication_year":2026,"publication_date":"2026-05-18","ids":{"openalex":"https://openalex.org/W4416854088","doi":"https://doi.org/10.1109/infocom59046.2026.11571467"},"language":"en","primary_location":{"id":"doi:10.1109/infocom59046.2026.11571467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom59046.2026.11571467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.07675","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103007400","display_name":"Xutong Liu","orcid":"https://orcid.org/0000-0002-8628-5873"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xutong Liu","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120673959","display_name":"Baran Atalar","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baran Atalar","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079056866","display_name":"Xiangxiang Dai","orcid":"https://orcid.org/0000-0003-0179-196X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiangxiang Dai","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085050673","display_name":"Jinhang Zuo","orcid":"https://orcid.org/0000-0002-9557-3551"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jinhang Zuo","raw_affiliation_strings":["City University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068905208","display_name":"Siwei Wang","orcid":"https://orcid.org/0009-0005-9748-7664"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Siwei Wang","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068489266","display_name":"John C. S. Lui","orcid":"https://orcid.org/0000-0001-7466-0384"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"John C.S. Lui","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344589","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0003-4065-9830"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085243096","display_name":"Carlee Joe\u2010Wong","orcid":"https://orcid.org/0000-0003-0785-9291"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlee Joe-Wong","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.6503000259399414,"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"}},"topics":[{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.6503000259399414,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.09380000084638596,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.023900000378489494,"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/cache","display_name":"Cache","score":0.6402999758720398},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6306999921798706},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6270999908447266},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.5544000267982483},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47209998965263367},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4406999945640564},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4350000023841858},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.421099990606308}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8880000114440918},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6402999758720398},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6306999921798706},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6270999908447266},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.5544000267982483},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47209998965263367},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4406999945640564},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.421099990606308},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41519999504089355},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32519999146461487},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.32339999079704285},{"id":"https://openalex.org/C2778180026","wikidata":"https://www.wikidata.org/wiki/Q18378163","display_name":"Semantic heterogeneity","level":4,"score":0.3221000134944916},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.310699999332428},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3070000112056732},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.2838999927043915},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2705000042915344}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/infocom59046.2026.11571467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom59046.2026.11571467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.07675","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.07675","pdf_url":"https://arxiv.org/pdf/2508.07675","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:doi:10.48550/arxiv.2508.07675","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2508.07675","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.07675","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.07675","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.07675","pdf_url":"https://arxiv.org/pdf/2508.07675","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4,101,114],"revolutionizing":[5],"how":[6],"users":[7],"interact":[8],"with":[9,163,186],"information":[10],"systems,":[11],"yet":[12],"their":[13],"high":[14],"inference":[15,24],"cost":[16,144],"poses":[17],"serious":[18],"scalability":[19],"and":[20,86,98,104,120,143,151,158],"sustainability":[21],"challenges.":[22],"Caching":[23],"responses,":[25],"allowing":[26],"them":[27],"to":[28,55,122,124],"be":[29,106],"retrieved":[30],"without":[31],"another":[32],"forward":[33],"pass":[34],"through":[35],"the":[36,49,156],"LLM,":[37],"has":[38],"emerged":[39],"as":[40,94],"one":[41,77],"possible":[42],"solution.":[43],"Traditional":[44],"exact-match":[45],"caching,":[46],"however,":[47],"overlooks":[48],"semantic":[50,67,111,137],"similarity":[51],"between":[52,83],"queries,":[53],"leading":[54],"unnecessary":[56],"recomputation.":[57],"Semantic":[58],"caching":[59,112],"addresses":[60],"this":[61,128],"by":[62],"retrieving":[63],"responses":[64],"based":[65],"on":[66,171],"similarity,":[68],"but":[69],"introduces":[70],"a":[71,132,172],"fundamentally":[72],"different":[73],"cache":[74,138],"eviction":[75,139],"problem:":[76],"must":[78,105],"account":[79],"for":[80,136],"mismatch":[81],"costs":[82],"incoming":[84],"queries":[85],"cached":[87],"responses.":[88],"Moreover,":[89],"key":[90],"system":[91],"parameters,":[92],"such":[93],"query":[95,142],"arrival":[96],"probabilities":[97],"serving":[99],"costs,":[100],"often":[102],"unknown":[103,141],"learned":[107],"over":[108],"time.":[109],"Existing":[110],"methods":[113],"largely":[115],"ad-hoc,":[116],"lacking":[117],"theoretical":[118],"foundations":[119],"unable":[121],"adapt":[123],"real-world":[125],"uncertainty.":[126],"In":[127],"paper,":[129],"we":[130],"present":[131],"principled,":[133],"learning-based":[134],"framework":[135,170],"under":[140],"distributions.":[145],"We":[146,166],"formulate":[147],"both":[148],"offline":[149],"optimization":[150],"online":[152],"learning":[153],"variants":[154],"of":[155],"problem,":[157],"develop":[159],"provably":[160],"efficient":[161],"algorithms":[162,179],"state-of-the-art":[164],"guarantees.":[165],"also":[167],"evaluate":[168],"our":[169,177],"synthetic":[173],"dataset,":[174],"showing":[175],"that":[176],"proposed":[178],"perform":[180],"matching":[181],"or":[182],"superior":[183],"performance":[184],"compared":[185],"baselines.":[187]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}