{"id":"https://openalex.org/W4416016571","doi":"https://doi.org/10.1145/3746252.3761340","title":"Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study","display_name":"Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416016571","doi":"https://doi.org/10.1145/3746252.3761340"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761340","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-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":"Shuo Yu","orcid":"https://orcid.org/0009-0006-1060-5451"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Yu","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0006-1060-5451","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054174049","display_name":"Mingyue Cheng","orcid":"https://orcid.org/0000-0001-9873-7681"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyue Cheng","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9873-7681","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453156","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0001-6956-5550"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Liu","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6956-5550","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068700447","display_name":"Daoyu Wang","orcid":"https://orcid.org/0009-0002-0452-0516"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daoyu Wang","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0002-0452-0516","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098953125","display_name":"Jiqian Yang","orcid":"https://orcid.org/0009-0007-6421-2626"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqian Yang","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0007-6421-2626","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111962380","display_name":"Jie Ouyang","orcid":"https://orcid.org/0009-0001-7652-368X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Ouyang","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0001-7652-368X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017352895","display_name":"Yucong Luo","orcid":"https://orcid.org/0000-0003-0685-0834"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yucong Luo","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-0685-0834","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046590511","display_name":"Chenyi Lei","orcid":"https://orcid.org/0000-0001-6287-3673"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyi Lei","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6287-3673","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048237545","display_name":"Enhong Chen","orcid":"https://orcid.org/0000-0002-4835-4102"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enhong Chen","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4835-4102","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5175,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93673713,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3931","last_page":"3941"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.46950000524520874,"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":0.46950000524520874,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3061000108718872,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.07169999927282333,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6804999709129333},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6654000282287598},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6636000275611877},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.6075000166893005},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4431000053882599},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.4032999873161316},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.34049999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7635999917984009},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6804999709129333},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6654000282287598},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6636000275611877},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.6075000166893005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5830000042915344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5421000123023987},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4431000053882599},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41990000009536743},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34049999713897705},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2653000056743622}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3761340","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7967803912","display_name":null,"funder_award_id":"62502486","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2788330850","https://openalex.org/W2912924812","https://openalex.org/W4207008429","https://openalex.org/W4224320476","https://openalex.org/W4309674289","https://openalex.org/W4318812099","https://openalex.org/W4390344084","https://openalex.org/W4391876619","https://openalex.org/W4392822469","https://openalex.org/W4402670856","https://openalex.org/W4403560390","https://openalex.org/W4404351611","https://openalex.org/W4411630045"],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"is":[3,61,113],"increasingly":[4],"recognized":[5],"as":[6,161,163],"an":[7],"effective":[8],"approach":[9],"to":[10,120],"mitigating":[11],"the":[12,20,62,75,114,122,148,175,182],"hallucination":[13],"of":[14,22,35,64,74,116,124,158,177],"large":[15],"language":[16],"models":[17],"(LLMs)":[18],"through":[19],"integration":[21,123],"external":[23,36],"knowledge.":[24],"While":[25],"numerous":[26],"efforts,":[27],"most":[28,43],"studies":[29],"focus":[30],"on":[31,99],"a":[32,65,84,105,156],"single":[33],"type":[34],"knowledge":[37,47,70,92],"source.":[38],"However,":[39],"in":[40,181],"real-world":[41],"applications,":[42],"situations":[44],"involve":[45],"diverse":[46,94],"from":[48],"various":[49,136],"sources,":[50],"yet":[51],"this":[52,100],"area":[53],"has":[54],"been":[55],"less":[56],"explored.":[57],"The":[58],"main":[59,111],"dilemma":[60],"lack":[63],"suitable":[66],"dataset":[67,86,150,167],"containing":[68],"multiple":[69],"sources":[71],"and":[72,90,95,143,151,168],"pre-exploration":[73],"associated":[76],"issues.":[77],"To":[78],"address":[79],"these":[80],"challenges,":[81],"we":[82,102,153],"standardize":[83],"benchmark":[85],"that":[87],"combines":[88],"structured":[89],"unstructured":[91],"across":[93,135],"complementary":[96],"domains.":[97],"Based":[98],"dataset,":[101],"further":[103],"develop":[104],"plug-and-play":[106],"RAG":[107,138,183],"framework,":[108],"PruningRAG,":[109,152],"whose":[110],"characteristic":[112],"use":[115],"multi-granularity":[117],"pruning":[118],"strategies":[119],"optimize":[121],"relevant":[125],"information":[126],"while":[127],"minimizing":[128],"misleading":[129],"context.":[130],"It":[131],"consistently":[132],"improves":[133],"performance":[134],"existing":[137],"variants,":[139],"demonstrating":[140],"its":[141],"robustness":[142],"broad":[144],"applicability.":[145],"Building":[146],"upon":[147],"standardized":[149],"also":[154],"report":[155],"series":[157],"experimental":[159],"results,":[160],"well":[162],"insightful":[164],"findings.":[165],"Our":[166],"code":[169],"are":[170],"publicly":[171],"available.":[172],"https://github.com/USTCAGI/PruningRAG,":[173],"with":[174],"aim":[176],"advancing":[178],"future":[179],"research":[180],"community.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}