{"id":"https://openalex.org/W7166737774","doi":"https://doi.org/10.1145/3808190","title":"Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks","display_name":"Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7166737774","doi":"https://doi.org/10.1145/3808190"},"language":"en","primary_location":{"id":"doi:10.1145/3808190","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3808190","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3808190","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118139646","display_name":"Qiang Ke","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":false,"raw_author_name":"Qiang Ke","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0003-2520-881X","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/A5023970004","display_name":"Yanjie Zhao","orcid":"https://orcid.org/0000-0001-8793-5367"},"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":"Yanjie Zhao","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-8793-5367","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/A5139698216","display_name":"Hongjin Leng","orcid":"https://orcid.org/0009-0007-3607-8204"},"institutions":[{"id":"https://openalex.org/I4210134189","display_name":"Xiamen University Malaysia","ror":"https://ror.org/0331wa828","country_code":"MY","type":"education","lineage":["https://openalex.org/I191208505","https://openalex.org/I4210134189"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Hongjin Leng","raw_affiliation_strings":["Xiamen University Malaysia, Sepang, Malaysia"],"raw_orcid":"https://orcid.org/0009-0007-3607-8204","affiliations":[{"raw_affiliation_string":"Xiamen University Malaysia, Sepang, Malaysia","institution_ids":["https://openalex.org/I4210134189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102958575","display_name":"Shengming Zhao","orcid":"https://orcid.org/0009-0007-5035-2206"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengming Zhao","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-5035-2206","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115695530","display_name":"Haoyu Wang","orcid":"https://orcid.org/0000-0003-1100-8633"},"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":"Haoyu Wang","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-1100-8633","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8991255,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":"FSE","first_page":"4161","last_page":"4183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.8862000107765198,"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/T10260","display_name":"Software Engineering Research","score":0.8862000107765198,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.04859999939799309,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.007199999876320362,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/empirical-research","display_name":"Empirical research","score":0.625},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.535099983215332},{"id":"https://openalex.org/keywords/search-based-software-engineering","display_name":"Search-based software engineering","score":0.4754999876022339},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.47269999980926514},{"id":"https://openalex.org/keywords/software-system","display_name":"Software system","score":0.4569000005722046},{"id":"https://openalex.org/keywords/software-construction","display_name":"Software construction","score":0.4235999882221222},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.42329999804496765},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.40049999952316284},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.38350000977516174},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.3785000145435333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6802999973297119},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.625},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5906000137329102},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C139143892","wikidata":"https://www.wikidata.org/wiki/Q7441615","display_name":"Search-based software engineering","level":5,"score":0.4754999876022339},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.47269999980926514},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.4569000005722046},{"id":"https://openalex.org/C186846655","wikidata":"https://www.wikidata.org/wiki/Q3398377","display_name":"Software construction","level":4,"score":0.4235999882221222},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.42329999804496765},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.40049999952316284},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.38350000977516174},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3537999987602234},{"id":"https://openalex.org/C509989072","wikidata":"https://www.wikidata.org/wiki/Q15188241","display_name":"Model-driven architecture","level":4,"score":0.34790000319480896},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C151552104","wikidata":"https://www.wikidata.org/wiki/Q7705809","display_name":"Test suite","level":4,"score":0.3278999924659729},{"id":"https://openalex.org/C174683762","wikidata":"https://www.wikidata.org/wiki/Q609588","display_name":"Component-based software engineering","level":4,"score":0.32519999146461487},{"id":"https://openalex.org/C145644426","wikidata":"https://www.wikidata.org/wiki/Q169411","display_name":"Unified Modeling Language","level":3,"score":0.3068000078201294},{"id":"https://openalex.org/C52913732","wikidata":"https://www.wikidata.org/wiki/Q857102","display_name":"Software design","level":4,"score":0.3052000105381012},{"id":"https://openalex.org/C207850805","wikidata":"https://www.wikidata.org/wiki/Q269608","display_name":"Reverse engineering","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2992999851703644},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.28929999470710754},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.2782999873161316},{"id":"https://openalex.org/C2984968299","wikidata":"https://www.wikidata.org/wiki/Q1077784","display_name":"Software tool","level":3,"score":0.27250000834465027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26899999380111694},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.26499998569488525},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2621000111103058},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.2590999901294708},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2563000023365021},{"id":"https://openalex.org/C133199616","wikidata":"https://www.wikidata.org/wiki/Q25386885","display_name":"Empirical modelling","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C86610423","wikidata":"https://www.wikidata.org/wiki/Q1925081","display_name":"Metamodeling","level":2,"score":0.25099998712539673},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3808190","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3808190","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3808190","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3808190","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2051204868","https://openalex.org/W2123246351","https://openalex.org/W2144211451","https://openalex.org/W2148972377","https://openalex.org/W2964150020","https://openalex.org/W2998702515","https://openalex.org/W3035390927","https://openalex.org/W3098605233","https://openalex.org/W3099700870","https://openalex.org/W3156789018","https://openalex.org/W3208407575","https://openalex.org/W4285149002","https://openalex.org/W4288055447","https://openalex.org/W4327652987","https://openalex.org/W4385565351","https://openalex.org/W4401043431","https://openalex.org/W4401856724","https://openalex.org/W4402670856","https://openalex.org/W4402671835","https://openalex.org/W4402672004","https://openalex.org/W4402684113","https://openalex.org/W4404782883","https://openalex.org/W4404835216","https://openalex.org/W4407580437","https://openalex.org/W4411233295","https://openalex.org/W4415746005"],"related_works":[],"abstract_inverted_index":{"While":[0],"Retrieval-Augmented":[1],"Generation":[2],"(RAG)":[3],"is":[4],"increasingly":[5],"adopted":[6],"to":[7],"ground":[8],"Large":[9],"Language":[10],"Models":[11],"(LLMs)":[12],"in":[13],"software":[14,27,177],"artifacts,":[15],"the":[16,52,113,117,120,134,137,141],"optimal":[17],"configuration":[18],"of":[19,33,96,119,136],"its":[20],"components":[21,92],"remains":[22],"an":[23],"open":[24],"question":[25],"for":[26,160,176],"engineering":[28,178],"(SE)":[29],"tasks.":[30,152],"The":[31],"lack":[32],"systematic":[34],"guidance":[35,166],"forces":[36],"practitioners":[37],"into":[38],"costly,":[39],"ad-hoc":[40],"experimentation.":[41],"This":[42],"paper":[43],"presents":[44],"a":[45,94,110,125,156],"comprehensive,":[46],"component-wise":[47],"empirical":[48,107],"study":[49,63],"that":[50],"dissects":[51],"RAG":[53,174],"pipeline,":[54],"evaluating":[55],"over":[56],"21":[57],"distinct":[58,87],"models":[59,74],"and":[60,66,78,85,104,162],"methods.":[61],"Our":[62,106,153],"systematically":[64],"isolates":[65],"evaluates":[67],"4":[68,81],"query":[69],"processing":[70],"techniques,":[71],"7":[72],"retrieval":[73,121],"spanning":[75],"sparse,":[76],"dense,":[77],"hybrid":[79],"paradigms,":[80],"context":[82],"refinement":[83],"methods,":[84],"6":[86],"generators.":[88],"We":[89],"test":[90],"these":[91],"on":[93,129,167],"suite":[95],"3":[97],"core":[98],"SE":[99],"tasks:":[100],"code":[101],"generation,":[102],"summarization,":[103],"repair.":[105],"findings":[108],"reveal":[109],"crucial":[111],"insight:":[112],"retriever-side":[114],"components,":[115],"particularly":[116],"choice":[118],"algorithm,":[122],"often":[123],"exert":[124],"more":[126],"significant":[127],"influence":[128],"final":[130],"system":[131],"performance":[132,149],"than":[133],"selection":[135],"generator":[138],"model.":[139],"Strikingly,":[140],"classic":[142],"lexical":[143],"retriever":[144],"BM25":[145],"demonstrates":[146],"exceptionally":[147],"robust":[148],"across":[150],"diverse":[151],"analysis":[154],"provides":[155],"practical,":[157],"data-driven":[158],"roadmap":[159],"researchers":[161],"practitioners,":[163],"offering":[164],"clear":[165],"prioritizing":[168],"optimization":[169],"efforts":[170],"when":[171],"constructing":[172],"effective":[173],"systems":[175],"contexts.":[179]},"counts_by_year":[],"updated_date":"2026-07-02T06:12:58.138171","created_date":"2026-07-01T00:00:00"}
