{"id":"https://openalex.org/W7164304091","doi":"https://doi.org/10.48550/arxiv.2606.11907","title":"Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generation","display_name":"Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generation","publication_year":2026,"publication_date":"2026-06-10","ids":{"openalex":"https://openalex.org/W7164304091","doi":"https://doi.org/10.48550/arxiv.2606.11907"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.11907","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11907","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.11907","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133128829","display_name":"Ziyu Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Ziyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138474835","display_name":"Jiaming Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Jiaming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138429521","display_name":"Kuangyu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Kuangyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001623354","display_name":"Tuo Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Tuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138405133","display_name":"Chuanpeng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chuanpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.8920000195503235,"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":0.8920000195503235,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.022600000724196434,"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/T11269","display_name":"Algorithms and Data Compression","score":0.017500000074505806,"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/robustness","display_name":"Robustness (evolution)","score":0.6771000027656555},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5813999772071838},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5062000155448914},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.42480000853538513},{"id":"https://openalex.org/keywords/extreme-value-theory","display_name":"Extreme value theory","score":0.423799991607666},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4124999940395355},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.40059998631477356},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.39489999413490295}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6771000027656555},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5813999772071838},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5062000155448914},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47119998931884766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.435699999332428},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.42480000853538513},{"id":"https://openalex.org/C147581598","wikidata":"https://www.wikidata.org/wiki/Q729429","display_name":"Extreme value theory","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42170000076293945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41499999165534973},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34850001335144043},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34380000829696655},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3434999883174896},{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C182964748","wikidata":"https://www.wikidata.org/wiki/Q208216","display_name":"Triangle inequality","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2962999939918518},{"id":"https://openalex.org/C2778217198","wikidata":"https://www.wikidata.org/wiki/Q556977","display_name":"Cutoff","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C39847760","wikidata":"https://www.wikidata.org/wiki/Q1385465","display_name":"Extreme point","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.11907","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11907","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.11907","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11907","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Adaptive":[0],"context":[1],"selection":[2],"is":[3,68],"critical":[4],"for":[5,30],"retrieval-augmented":[6],"generation":[7],"(RAG)":[8],"systems,":[9],"as":[10],"fixed":[11],"Top-K":[12],"retrieval":[13,159],"fails":[14],"under":[15],"query-dependent":[16],"and":[17,47,152,180],"heavy-tailed":[18],"similarity":[19,71],"distributions.":[20],"While":[21],"Extreme":[22],"Value":[23],"Theory":[24],"(EVT)":[25],"offers":[26],"a":[27,54,61,74,79,96,138],"principled":[28],"framework":[29,56],"adaptive":[31],"truncation,":[32],"existing":[33],"approaches":[34],"apply":[35],"EVT":[36,59,172],"globally":[37],"across":[38,177],"the":[39,110,144],"entire":[40],"ranked":[41,70],"list,":[42],"incurring":[43],"prohibitive":[44],"computational":[45,119],"costs":[46],"statistical":[48,128],"instability.":[49],"We":[50],"propose":[51],"Tail-Aware":[52],"Adaptive-k(TAA-k),":[53],"training-free":[55],"that":[57,69,155],"operationalizes":[58],"through":[60],"localized":[62],"validation":[63],"strategy.":[64],"The":[65],"key":[66],"insight":[67],"curves":[72],"exhibit":[73],"characteristic":[75],"steep--flat--steep":[76],"pattern":[77],"reflecting":[78],"transition":[80],"from":[81,121],"relevance-dominated":[82],"to":[83,94,108,123,143],"noise-dominated":[84,146],"regimes.":[85],"TAA-k":[86,136,156],"exploits":[87],"this":[88,106],"geometric":[89],"structure":[90],"via":[91],"knee":[92],"detection":[93],"identify":[95],"compact":[97],"candidate":[98],"region,":[99],"then":[100],"applies":[101],"EVT-based":[102],"goodness-of-fit":[103],"testing":[104],"within":[105,162],"window":[107],"validate":[109],"onset":[111],"of":[112,164],"tail":[113],"behavior.":[114],"This":[115],"coarse-to-fine":[116],"design":[117],"reduces":[118],"complexity":[120],"O(N^2M)":[122],"O(sqrt{N\\log":[124],"N}*M)":[125],"while":[126,174],"maintaining":[127,175],"rigor.":[129],"Under":[130],"mild":[131],"monotone":[132],"likelihood":[133],"ratio":[134],"assumptions,":[135],"yields":[137],"stable,":[139],"query-adaptive":[140],"cutoff":[141],"corresponding":[142],"earliest":[145],"position.":[147],"Experiments":[148],"on":[149],"WebQuestions,":[150],"2WikiMultiHopQA,":[151],"MuSiQue":[153],"demonstrate":[154],"achieves":[157],"near-oracle":[158],"quality":[160],"(F1":[161],"2-3%":[163],"oracle)":[165],"with":[166],"orders-of-magnitude":[167],"efficiency":[168],"gains":[169],"over":[170],"global":[171],"methods,":[173],"robustness":[176],"embedding":[178],"models":[179],"compression":[181],"dimensions.":[182]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-12T00:00:00"}