{"id":"https://openalex.org/W7155012758","doi":"https://doi.org/10.48550/arxiv.2604.15621","title":"Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking","display_name":"Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking","publication_year":2026,"publication_date":"2026-04-17","ids":{"openalex":"https://openalex.org/W7155012758","doi":"https://doi.org/10.48550/arxiv.2604.15621"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.15621","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15621","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.15621","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134084597","display_name":"Jun Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Jun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103182335","display_name":"Jiahui Tang","orcid":"https://orcid.org/0000-0002-4933-527X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jiahui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134018306","display_name":"Zhicheng He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Zhicheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134043239","display_name":"Hang Lv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lv, Hang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113346577","display_name":"Hongchao Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Hongchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134006455","display_name":"Hao Wang","orcid":"https://orcid.org/0009-0001-6738-4577"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134060525","display_name":"Xuezhi Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xuezhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134066743","display_name":"Shuai Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.572700023651123,"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":0.572700023651123,"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/T10028","display_name":"Topic Modeling","score":0.33739998936653137,"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":0.01489999983459711,"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":0.6373999714851379},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5317999720573425},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4814999997615814},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4526999890804291},{"id":"https://openalex.org/keywords/through-the-lens-metering","display_name":"Through-the-lens metering","score":0.44850000739097595},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4081000089645386},{"id":"https://openalex.org/keywords/adaptive-sampling","display_name":"Adaptive sampling","score":0.35370001196861267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7095999717712402},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6373999714851379},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5317999720573425},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4973999857902527},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4526999890804291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4507000148296356},{"id":"https://openalex.org/C43091099","wikidata":"https://www.wikidata.org/wiki/Q1067788","display_name":"Through-the-lens metering","level":3,"score":0.44850000739097595},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3776000142097473},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.35370001196861267},{"id":"https://openalex.org/C2982777018","wikidata":"https://www.wikidata.org/wiki/Q99268086","display_name":"Adaptive design","level":3,"score":0.34630000591278076},{"id":"https://openalex.org/C102248274","wikidata":"https://www.wikidata.org/wiki/Q168388","display_name":"Adaptive filter","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.2612000107765198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.15621","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15621","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.15621","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15621","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Adaptive":[0],"Retrieval-Augmented":[1],"Generation":[2],"aims":[3],"to":[4,29,88,159],"mitigate":[5],"the":[6,14,31,56],"interference":[7],"of":[8,16,33,58],"extraneous":[9],"noise":[10,154],"by":[11,110],"dynamically":[12],"determining":[13],"necessity":[15,32,44,57],"retrieving":[17],"supplementary":[18],"passages.":[19],"However,":[20],"as":[21,151,165],"Large":[22],"Language":[23],"Models":[24],"evolve":[25],"with":[26,72,93,134],"increasing":[27],"robustness":[28],"noise,":[30],"adaptive":[34,50,59,66,99,147],"retrieval":[35,51,85],"warrants":[36],"re-evaluation.":[37],"In":[38],"this":[39,43,94],"paper,":[40],"we":[41,62,102],"rethink":[42],"and":[45,77,98,113,121],"propose":[46],"AdaRankLLM,":[47],"a":[48,69,73,104,143,152,166],"novel":[49],"framework.":[52],"To":[53],"effectively":[54],"verify":[55],"listwise":[60,96],"reranking,":[61],"first":[63],"develop":[64],"an":[65],"ranker":[67],"employing":[68],"zero-shot":[70],"prompt":[71],"passage":[74],"dropout":[75],"mechanism,":[76],"compare":[78],"its":[79],"generation":[80],"outcomes":[81],"against":[82],"static":[83],"fixed-depth":[84],"strategies.":[86],"Furthermore,":[87],"endow":[89],"smaller":[90],"open-source":[91],"LLMs":[92,123],"precise":[95],"ranking":[97],"filtering":[100],"capability,":[101],"introduce":[103],"two-stage":[105],"progressive":[106],"distillation":[107],"paradigm":[108],"enhanced":[109],"data":[111],"sampling":[112],"augmentation":[114],"techniques.":[115],"Extensive":[116],"experiments":[117],"across":[118],"three":[119],"datasets":[120],"eight":[122],"demonstrate":[124],"that":[125],"AdaRankLLM":[126],"consistently":[127],"achieves":[128],"optimal":[129],"performance":[130],"in":[131,146],"most":[132],"scenarios":[133],"significantly":[135],"reduced":[136],"context":[137],"overhead.":[138],"Crucially,":[139],"our":[140],"analysis":[141],"reveals":[142],"role":[144],"shift":[145],"retrieval:":[148],"it":[149],"functions":[150],"critical":[153],"filter":[155],"for":[156,170],"weaker":[157],"models":[158],"overcome":[160],"their":[161],"limitations,":[162],"while":[163],"serving":[164],"cost-effective":[167],"efficiency":[168],"optimizer":[169],"stronger":[171],"reasoning":[172],"models.":[173]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-21T00:00:00"}