{"id":"https://openalex.org/W7108338987","doi":"https://doi.org/10.1145/3767695.3769518","title":"On the Diminishing Returns of Complex Robust RAG Training in the Era of Powerful LLMs","display_name":"On the Diminishing Returns of Complex Robust RAG Training in the Era of Powerful LLMs","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7108338987","doi":"https://doi.org/10.1145/3767695.3769518"},"language":null,"primary_location":{"id":"doi:10.1145/3767695.3769518","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769518","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3767695.3769518","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hanxing Ding","orcid":"https://orcid.org/0009-0003-5000-3429"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanxing Ding","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-5000-3429","affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuchang Tao","orcid":"https://orcid.org/0000-0001-6113-6145"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuchang Tao","raw_affiliation_strings":["Tongyi Lab, Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6113-6145","affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liang Pang","orcid":"https://orcid.org/0000-0003-1161-8546"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Pang","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1161-8546","affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zihao Wei","orcid":"https://orcid.org/0000-0002-5836-0282"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Wei","raw_affiliation_strings":["Institute of Computing Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5836-0282","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liwei Chen","orcid":"https://orcid.org/0009-0006-6101-503X"},"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":"Liwei Chen","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-6101-503X","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kun Xu","orcid":"https://orcid.org/0000-0002-3863-344X"},"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":"Kun Xu","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3863-344X","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huawei Shen","orcid":"https://orcid.org/0000-0002-1081-8119"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huawei Shen","raw_affiliation_strings":["Institute of Computing Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1081-8119","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqi Cheng","raw_affiliation_strings":["Institute of Computing Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5201-8195","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4214000105857849,"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":0.4214000105857849,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.2784999907016754,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10320000350475311,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7473000288009644},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5516999959945679},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5281999707221985},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.44600000977516174},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3138999938964844},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.289000004529953}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7473000288009644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5529999732971191},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5516999959945679},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5281999707221985},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40950000286102295},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.40049999952316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.376800000667572},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.32260000705718994},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.3102000057697296},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C47822265","wikidata":"https://www.wikidata.org/wiki/Q854457","display_name":"Complex system","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C138551086","wikidata":"https://www.wikidata.org/wiki/Q842271","display_name":"Marginal utility","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.265500009059906}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3767695.3769518","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769518","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:10.1145/3767695.3769518","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769518","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2252136820","https://openalex.org/W2889787757","https://openalex.org/W2912924812","https://openalex.org/W2963339397","https://openalex.org/W4383987670","https://openalex.org/W4389403907","https://openalex.org/W4389519118","https://openalex.org/W4402701389","https://openalex.org/W6967255466"],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"systems":[3],"traditionally":[4],"employ":[5],"sophisticated":[6,60],"training":[7,30,61,94,118,135],"strategies":[8,62],"to":[9],"enhance":[10],"robustness":[11,57],"against":[12],"retrieval":[13],"noise.":[14],"In":[15],"this":[16],"work,":[17],"we":[18],"investigate":[19],"a":[20,52],"critical":[21],"question:":[22],"does":[23],"the":[24,55,128],"benefit":[25,58],"of":[26,59],"these":[27],"complex":[28,77,133],"robust":[29,134],"methods":[31],"diminish":[32],"as":[33,65,124],"language":[34],"models":[35,71,85,101,126,149],"become":[36],"more":[37,83,111],"powerful?":[38],"Through":[39],"systematic":[40],"evaluation":[41],"across":[42],"multiple":[43],"model":[44,66],"scales":[45],"and":[46,80,110],"question-answering":[47],"datasets,":[48],"our":[49],"analysis":[50],"reveals":[51],"consistent":[53],"trend:":[54],"marginal":[56],"decreases":[63],"substantially":[64],"capacity":[67],"increases.":[68],"While":[69],"smaller":[70],"show":[72],"significant":[73],"performance":[74,91],"improvements":[75],"from":[76],"document":[78],"selection":[79],"adversarial":[81],"objectives,":[82],"capable":[84],"achieve":[86],"comparable":[87],"or":[88],"even":[89,115],"superior":[90],"with":[92],"simpler":[93],"approaches.":[95],"Further":[96],"investigation":[97],"demonstrates":[98],"that":[99,123,141],"stronger":[100],"naturally":[102],"exhibit":[103],"better":[104],"confidence":[105],"calibration,":[106],"cross-dataset":[107],"generalization":[108],"capability,":[109],"effective":[112],"attention":[113],"patterns,":[114],"under":[116],"simple":[117],"regimes.":[119],"These":[120],"findings":[121],"suggest":[122],"foundation":[125],"evolve,":[127],"engineering":[129],"effort":[130],"invested":[131],"in":[132],"may":[136],"yield":[137],"diminishing":[138],"returns,":[139],"indicating":[140],"simplified":[142],"RAG":[143],"pipelines":[144],"could":[145],"suffice":[146],"for":[147],"powerful":[148],"while":[150],"maintaining":[151],"competitive":[152],"performance.":[153]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-03T00:00:00"}