{"id":"https://openalex.org/W7108329187","doi":"https://doi.org/10.1145/3767695.3769496","title":"Distilling a Small Utility-Based Passage Selector to Enhance Retrieval-Augmented Generation","display_name":"Distilling a Small Utility-Based Passage Selector to Enhance Retrieval-Augmented Generation","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7108329187","doi":"https://doi.org/10.1145/3767695.3769496"},"language":null,"primary_location":{"id":"doi:10.1145/3767695.3769496","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769496","pdf_url":null,"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 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3767695.3769496","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hengran Zhang","orcid":"https://orcid.org/0009-0004-1144-1298"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengran Zhang","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-1144-1298","affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Keping Bi","orcid":"https://orcid.org/0000-0001-5123-4999"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keping Bi","raw_affiliation_strings":["State Key Laboratory of AI Safety, ICT, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5123-4999","affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, ICT, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiafeng Guo","orcid":"https://orcid.org/0000-0002-9509-8674"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafeng Guo","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9509-8674","affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiaming Zhang","orcid":"https://orcid.org/0009-0009-8687-4713"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Zhang","raw_affiliation_strings":["Baidu Inc, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-8687-4713","affiliations":[{"raw_affiliation_string":"Baidu Inc, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuaiqiang Wang","orcid":"https://orcid.org/0000-0002-9212-1947"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuaiqiang Wang","raw_affiliation_strings":["Baidu Inc, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9212-1947","affiliations":[{"raw_affiliation_string":"Baidu Inc, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dawei Yin","orcid":"https://orcid.org/0000-0002-0684-6205"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Yin","raw_affiliation_strings":["Baidu Inc, Beijing, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0684-6205","affiliations":[{"raw_affiliation_string":"Baidu Inc, Beijing, CA, USA","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xueqi Cheng","orcid":"https://orcid.org/0000-0002-5201-8195"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqi Cheng","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5201-8195","affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89055223,"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":"22","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6873000264167786,"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":0.6873000264167786,"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":0.09200000017881393,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.04769999906420708,"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/ranking","display_name":"Ranking (information retrieval)","score":0.892300009727478},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.838699996471405},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.7932000160217285},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5929999947547913},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.49889999628067017},{"id":"https://openalex.org/keywords/empirical-evidence","display_name":"Empirical evidence","score":0.359499990940094},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.35440000891685486}],"concepts":[{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.892300009727478},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.838699996471405},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7932000160217285},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7422999739646912},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5929999947547913},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.49889999628067017},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4986000061035156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4348999857902527},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4088999927043915},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29670000076293945},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C2778363899","wikidata":"https://www.wikidata.org/wiki/Q23900955","display_name":"Window of opportunity","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.26489999890327454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3767695.3769496","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769496","pdf_url":null,"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 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3767695.3769496","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769496","pdf_url":null,"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 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7169767618179321}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2108862644","https://openalex.org/W2143331230","https://openalex.org/W2151012289","https://openalex.org/W2470818894","https://openalex.org/W2740492458","https://openalex.org/W2889787757","https://openalex.org/W2912924812","https://openalex.org/W2945802750","https://openalex.org/W3035324702","https://openalex.org/W3147292006","https://openalex.org/W3180230246","https://openalex.org/W4252076394","https://openalex.org/W4384890816","https://openalex.org/W4400525230","https://openalex.org/W4409657425","https://openalex.org/W4409670826"],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1,132,212],"(RAG)":[2],"enhances":[3],"large":[4],"language":[5],"models":[6,128],"(LLMs)":[7],"by":[8],"incorporating":[9],"retrieved":[10],"information.":[11,81],"Standard":[12],"retrieval":[13,53],"process":[14],"prioritized":[15],"relevance,":[16],"focusing":[17],"on":[18,105],"topical":[19],"alignment":[20],"between":[21],"queries":[22,78,118],"and":[23,133,158,186,192,220],"passages.":[24,148],"In":[25],"contrast,":[26],"in":[27,54,209,232],"RAG,":[28,55,162],"the":[29,37,49,56,67,91,120,173,179,217,225],"emphasis":[30],"has":[31],"shifted":[32],"to":[33,89,116,129],"utility,":[34],"which":[35],"considers":[36],"usefulness":[38],"of":[39,51,60,69,95],"passages":[40,70],"for":[41,63,76,122,161,182,198,224],"generating":[42],"accurate":[43],"answers.":[44],"Despite":[45],"empirical":[46],"evidence":[47],"showing":[48],"benefits":[50],"utility-based":[52,106,153,187,201,221],"high":[57],"computational":[58,165],"cost":[59],"using":[61,139,176],"LLMs":[62,96],"utility":[64,92,134],"judgments":[65,135],"limits":[66],"number":[68],"evaluated.":[71],"This":[72],"restriction":[73],"is":[74,203],"problematic":[75],"complex":[77,199],"requiring":[79],"extensive":[80],"To":[82],"address":[83],"this,":[84],"we":[85],"propose":[86],"a":[87,140,156],"method":[88,143],"distill":[90],"judgment":[93],"capabilities":[94],"into":[97,190],"smaller,":[98],"more":[99,204],"efficient":[100],"models.":[101],"Our":[102,149,194],"approach":[103],"focuses":[104],"selection":[107,114,154,202,222],"rather":[108],"than":[109,206],"ranking,":[110],"enabling":[111],"dynamic":[112],"passage":[113],"tailored":[115],"specific":[117],"without":[119],"need":[121],"fixed":[123],"thresholds.":[124],"We":[125,171,214],"train":[126],"student":[127],"learn":[130],"pseudo-answer":[131],"from":[136],"teacher":[137,180],"LLMs,":[138],"sliding":[141],"window":[142],"that":[144,152,197],"dynamically":[145],"selects":[146],"useful":[147],"experiments":[150],"demonstrate":[151],"provides":[155],"flexible":[157],"cost-effective":[159],"solution":[160],"significantly":[163],"reducing":[164],"costs":[166],"while":[167],"improving":[168],"answer":[169,211],"quality.":[170],"present":[172],"distillation":[174],"results":[175],"Qwen3-32B":[177],"as":[178],"model":[181],"both":[183],"relevance":[184,207,218],"ranking":[185,208,219],"selection,":[188],"distilled":[189],"RankQwen1.7B":[191],"UtilityQwen1.7B.":[193],"findings":[195],"indicate":[196],"questions,":[200],"effective":[205],"enhancing":[210],"performance.":[213],"will":[215],"release":[216],"annotations":[223],"MS":[226],"MARCO":[227],"dataset,":[228],"supporting":[229],"further":[230],"research":[231],"this":[233],"area.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-04T23:47:47.292601","created_date":"2025-12-03T00:00:00"}