{"id":"https://openalex.org/W4416035224","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.218","title":"How Does Knowledge Selection Help Retrieval Augmented Generation?","display_name":"How Does Knowledge Selection Help Retrieval Augmented Generation?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035224","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.218"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.218","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.218","pdf_url":"https://aclanthology.org/2025.findings-emnlp.218.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.218.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042303431","display_name":"Xiangci Li","orcid":"https://orcid.org/0000-0002-7493-9534"},"institutions":[{"id":"https://openalex.org/I2799847335","display_name":"Art Institute of Portland","ror":"https://ror.org/01cb0jg64","country_code":"US","type":"education","lineage":["https://openalex.org/I2799847335","https://openalex.org/I2799969541"]},{"id":"https://openalex.org/I87573096","display_name":"University of North Texas at Dallas","ror":"https://ror.org/01n51v443","country_code":"US","type":"education","lineage":["https://openalex.org/I87573096"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangci Li","raw_affiliation_strings":["AWS AI Labs ,","University of Texas at Dallas lmsys/ chatbot-arena-leaderboard"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs ,","institution_ids":["https://openalex.org/I2799847335"]},{"raw_affiliation_string":"University of Texas at Dallas lmsys/ chatbot-arena-leaderboard","institution_ids":["https://openalex.org/I87573096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006011780","display_name":"Jessica Ouyang","orcid":"https://orcid.org/0000-0002-6835-8178"},"institutions":[{"id":"https://openalex.org/I87573096","display_name":"University of North Texas at Dallas","ror":"https://ror.org/01n51v443","country_code":"US","type":"education","lineage":["https://openalex.org/I87573096"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jessica Ouyang","raw_affiliation_strings":["University of Texas at Dallas lmsys/ chatbot-arena-leaderboard"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas lmsys/ chatbot-arena-leaderboard","institution_ids":["https://openalex.org/I87573096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6643,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86736749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4104","last_page":"4121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.6549000144004822,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.6549000144004822,"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/T12607","display_name":"Personal Information Management and User Behavior","score":0.010900000110268593,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T10918","display_name":"Memory Processes and Influences","score":0.010300000198185444,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.46639999747276306},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.35010001063346863},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2867000102996826},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.28110000491142273},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.2630000114440918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6539000272750854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48399999737739563},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.46639999747276306},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31619998812675476},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2752000093460083},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2590999901294708},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.218","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.218","pdf_url":"https://aclanthology.org/2025.findings-emnlp.218.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.218","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.218","pdf_url":"https://aclanthology.org/2025.findings-emnlp.218.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035224.pdf","grobid_xml":"https://content.openalex.org/works/W4416035224.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1,11,32,53,81,125],"(RAG)":[2],"is":[3,121,139],"a":[4,17,65,135,159,167],"powerful":[5],"method":[6],"for":[7,30],"enhancing":[8,124],"natural":[9],"language":[10],"by":[12],"integrating":[13],"external":[14],"knowledge":[15,28,37,49,106,118,129,155,164],"into":[16],"model's":[18,89],"output.While":[19],"prior":[20],"work":[21],"has":[22],"demonstrated":[23],"the":[24,34,75,86,94,97,103,109,117,128,154,163],"importance":[25],"of":[26,36,68,77,96,105],"improving":[27,116,172],"retrieval":[29,60],"boosting":[31],"quality,":[33],"role":[35,170],"selection,":[38],"a.k.a.reranking":[39],"or":[40,148],"filtering,":[41],"remains":[42],"less":[43],"clear.This":[44],"paper":[45],"empirically":[46],"analyzes":[47],"how":[48],"selection":[50,62,107],"influences":[51],"downstream":[52,87],"performance":[54],"in":[55,171],"RAG":[56,111],"systems.By":[57],"simulating":[58],"different":[59],"and":[61,70,99,152,162],"conditions":[63],"through":[64],"controlled":[66],"mixture":[67],"gold":[69],"distractor":[71],"knowledge,":[72],"we":[73],"assess":[74],"impact":[76,104],"these":[78],"factors":[79],"on":[80,108,141],"outcomes.Our":[82],"findings":[83],"indicate":[84],"that":[85],"generator":[88,137,146],"capability,":[90],"as":[91,93],"well":[92],"complexity":[95],"task":[98],"dataset,":[100],"significantly":[101],"influence":[102],"overall":[110,173],"system":[112],"performance.In":[113],"typical":[114],"scenarios,":[115],"recall":[119],"score":[120,157],"key":[122],"to":[123],"outcomes,":[126],"with":[127],"selector":[130,165],"providing":[131],"limited":[132],"benefit":[133],"when":[134],"strong":[136],"model":[138],"used":[140],"clear,":[142],"well-defined":[143],"tasks.For":[144],"weaker":[145],"models":[147],"more":[149,168],"ambiguous":[150],"tasks":[151],"datasets,":[153],"F1":[156],"becomes":[158],"critical":[160],"factor,":[161],"plays":[166],"prominent":[169],"performance.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-11-08T00:00:00"}