{"id":"https://openalex.org/W4407357331","doi":"https://doi.org/10.1145/3709661","title":"AquaPipe: A Quality-Aware Pipeline for Knowledge Retrieval and Large Language Models","display_name":"AquaPipe: A Quality-Aware Pipeline for Knowledge Retrieval and Large Language Models","publication_year":2025,"publication_date":"2025-02-10","ids":{"openalex":"https://openalex.org/W4407357331","doi":"https://doi.org/10.1145/3709661"},"language":"en","primary_location":{"id":"doi:10.1145/3709661","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3709661","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","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":"https://openalex.org/A5048139595","display_name":"Renqiu Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Runjie Yu","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101717597","display_name":"Weizhou Huang","orcid":"https://orcid.org/0000-0002-8024-0789"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weizhou Huang","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010118449","display_name":"Shuhan Bai","orcid":"https://orcid.org/0000-0002-0842-7602"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhan Bai","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005773038","display_name":"Jian Zhou","orcid":"https://orcid.org/0000-0001-5295-4680"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhou","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062125860","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0001-9746-4714"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5048139595"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":7.0705,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95984001,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"3","issue":"1","first_page":"1","last_page":"26"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/pipeline","display_name":"Pipeline (software)","score":0.7607271671295166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6856204271316528},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6171686053276062},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4820009768009186},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4696677625179291},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1142340898513794}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7607271671295166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6856204271316528},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6171686053276062},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4820009768009186},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4696677625179291},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1142340898513794},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3709661","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3709661","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2275391676","display_name":null,"funder_award_id":"No. B07038","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G5274664909","display_name":null,"funder_award_id":"No.61821003, No.62372197, No. U22A2071, No.62102155","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G7046263226","display_name":null,"funder_award_id":"2022YFB4501100","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1978030011","https://openalex.org/W2107627518","https://openalex.org/W2124509324","https://openalex.org/W2133995768","https://openalex.org/W2145065594","https://openalex.org/W2165558283","https://openalex.org/W2204555070","https://openalex.org/W2294518132","https://openalex.org/W2560674852","https://openalex.org/W2797054769","https://openalex.org/W2851684562","https://openalex.org/W2945127593","https://openalex.org/W2963284996","https://openalex.org/W2963339397","https://openalex.org/W2963469388","https://openalex.org/W2963748441","https://openalex.org/W2970641574","https://openalex.org/W2984806015","https://openalex.org/W2998702515","https://openalex.org/W3011056378","https://openalex.org/W3029693508","https://openalex.org/W3099446234","https://openalex.org/W3099700870","https://openalex.org/W3105233790","https://openalex.org/W3174809957","https://openalex.org/W3196481040","https://openalex.org/W3199958362","https://openalex.org/W4205807230","https://openalex.org/W4285113563","https://openalex.org/W4285355789","https://openalex.org/W4312285477","https://openalex.org/W4323343765","https://openalex.org/W4367046898","https://openalex.org/W4388169576","https://openalex.org/W4393730224","https://openalex.org/W4401176373"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"knowledge":[1,84],"retrieval":[2,85],"methods":[3],"such":[4],"as":[5],"Approximate":[6],"Nearest":[7],"Neighbor":[8],"Search":[9],"(ANNS)":[10],"significantly":[11],"enhance":[12,90],"the":[13,36,53,65,71,81,91,104,114,121,128,135,150,155,162,181,188,205,209,212],"generation":[14,31],"quality":[15],"of":[16,39,56,67,83,107,157,183,190,204,208],"Large":[17],"Language":[18],"Models":[19],"(LLMs)":[20],"by":[21,145,193,217],"introducing":[22],"external":[23],"knowledge,":[24],"and":[25,70,86,165],"this":[26],"method":[27],"is":[28,219],"called":[29],"Retrieval-augmented":[30],"(RAG).":[32],"However,":[33],"due":[34],"to":[35,44,89,139,160,169,195,201,221],"rapid":[37],"growth":[38],"data":[40,47,96],"size,":[41],"ANNS":[42,69,170,192],"tends":[43],"store":[45],"large-scale":[46],"on":[48,134],"disk,":[49],"which":[50,63],"greatly":[51],"increases":[52],"response":[54,206],"time":[55,207],"RAG":[57,77],"systems.":[58],"This":[59],"paper":[60],"presents":[61],"AquaPipe,":[62],"pipelines":[64,143],"execution":[66],"disk-based":[68,191],"LLM":[72,136],"prefill":[73,115,152],"phase":[74,116],"in":[75,198],"an":[76],"system,":[78],"effectively":[79,140],"overlapping":[80],"latency":[82,189],"model":[87,138],"inference":[88],"overall":[92],"performance,":[93],"while":[94,211],"guaranteeing":[95],"quality.":[97],"First,":[98],"ANNS's":[99],"recall-aware":[100],"prefetching":[101,218],"strategy":[102],"enables":[103],"early":[105,147],"return":[106],"partial":[108],"text":[109],"with":[110],"acceptable":[111],"accuracy":[112],"so":[113],"can":[117],"launch":[118],"before":[119],"getting":[120],"full":[122],"results.":[123],"Then,":[124],"we":[125],"adaptively":[126],"choose":[127],"remove-after-prefill":[129],"or":[130],"re-prefill":[131],"strategies":[132],"based":[133],"cost":[137],"correct":[141],"disturbed":[142],"caused":[144,216],"wrong":[146],"returns.":[148],"Finally,":[149],"pipelined":[151],"dynamically":[153],"changes":[154],"granularity":[156],"chunk":[158],"size":[159],"balance":[161],"overlap":[163],"efficiency":[164],"GPU":[166],"efficiency,":[167],"adjusting":[168],"tasks":[171],"that":[172],"converge":[173],"at":[174],"different":[175],"speeds.":[176],"Our":[177],"experiments":[178],"have":[179],"demonstrated":[180],"effectiveness":[182],"AquaPipe.":[184],"It":[185],"successfully":[186],"masks":[187],"56%":[194],"99%,":[196],"resulting":[197],"a":[199],"1.3\u00d7":[200],"2.6\u00d7":[202],"reduction":[203],"RAG,":[210],"extra":[213],"recall":[214],"loss":[215],"limited":[220],"approximately":[222],"1%.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}