{"id":"https://openalex.org/W7166813301","doi":"https://doi.org/10.18653/v1/2026.acl-long.859","title":"SpecCache: Speculative KV Cache Reuse for Efficient RAG Serving","display_name":"SpecCache: Speculative KV Cache Reuse for Efficient RAG Serving","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166813301","doi":"https://doi.org/10.18653/v1/2026.acl-long.859"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.859","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.859","pdf_url":"https://aclanthology.org/2026.acl-long.859.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.859.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139850695","display_name":"Zijian Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zijian Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139850041","display_name":"Tao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139797158","display_name":"Shuangwu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuangwu Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122381872","display_name":"Shenghao Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shenghao Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139840401","display_name":"Guo Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139764188","display_name":"Qirui Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qirui Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123517869","display_name":"Jingxian Shuai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingxian Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122368694","display_name":"Yunpeng Hou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunpeng Hou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047787436","display_name":"Huasen He","orcid":"https://orcid.org/0000-0001-9963-019X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huasen He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139849785","display_name":"Jianyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80277157,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18861","last_page":"18871"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.46070000529289246,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.46070000529289246,"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/T10028","display_name":"Topic Modeling","score":0.2176000028848648,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.029500000178813934,"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/reuse","display_name":"Reuse","score":0.6171000003814697},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.47350001335144043},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.28360000252723694},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2524000108242035},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.24899999797344208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6777999997138977},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6171000003814697},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.47350001335144043},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3601999878883362},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2653000056743622},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.24899999797344208},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2418999969959259},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.2345000058412552}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.859","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.859","pdf_url":"https://aclanthology.org/2026.acl-long.859.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.859","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.859","pdf_url":"https://aclanthology.org/2026.acl-long.859.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5523049831390381}],"awards":[{"id":"https://openalex.org/G4736320777","display_name":null,"funder_award_id":"U23A20275","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166813301.pdf","grobid_xml":"https://content.openalex.org/works/W7166813301.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zijian":[0],"Wen,":[1],"Tao":[2],"Zhang,":[3],"Shuangwu":[4],"Chen,":[5,11],"Shenghao":[6],"Ye,":[7],"Yu":[8],"Guo,":[9],"Qirui":[10],"Jingxian":[12],"Shuai,":[13],"Yunpeng":[14],"Hou,":[15],"Huasen":[16],"He,":[17],"Jianyang.":[18],"Proceedings":[19],"of":[20,25],"the":[21,26],"64th":[22],"Annual":[23],"Meeting":[24],"Association":[27],"for":[28],"Computational":[29],"Linguistics":[30],"(Volume":[31],"1:":[32],"Long":[33],"Papers).":[34],"2026.":[35]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
