{"id":"https://openalex.org/W7225375494","doi":"https://doi.org/10.48550/arxiv.2611.08367","title":"CascadeFilter: Cost-Efficient Semantic Filtering with Joint Threshold Selection","display_name":"CascadeFilter: Cost-Efficient Semantic Filtering with Joint Threshold Selection","publication_year":2026,"publication_date":"2026-11-05","ids":{"openalex":"https://openalex.org/W7225375494","doi":"https://doi.org/10.48550/arxiv.2611.08367"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.08367","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.08367","pdf_url":"https://arxiv.org/pdf/2611.08367","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.08367","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133679935","display_name":"Yanji He","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Yanji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161022884","display_name":"Tao Zhong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161071442","display_name":"Hongyang Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hongyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161043543","display_name":"Xiaobo Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiaobo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161086189","display_name":"Mingyu Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Mingyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5161044573","display_name":"Wei Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wei","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/T10028","display_name":"Topic Modeling","score":0.7050999999046326,"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":0.7050999999046326,"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":0.18690000474452972,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.04190000146627426,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/semantic-filtering","display_name":"semantic filtering","score":0.9950000047683716},{"id":"https://openalex.org/keywords/threshold-selection","display_name":"threshold selection","score":0.9309999942779541},{"id":"https://openalex.org/keywords/cost-efficient-inference","display_name":"cost-efficient inference","score":0.5450000166893005},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7689999938011169},{"id":"https://openalex.org/keywords/multiple-testing","display_name":"multiple comparisons","score":0.6000000238418579},{"id":"https://openalex.org/keywords/evidence-extraction","display_name":"evidence extraction","score":0.609000027179718},{"id":"https://openalex.org/keywords/re-ranking","display_name":"re-ranking","score":0.9649999737739563},{"id":"https://openalex.org/keywords/confidence-estimation","display_name":"confidence estimation","score":0.593999981880188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.788100004196167},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.534500002861023},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4593000113964081},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4569999873638153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45249998569488525},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38530001044273376},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C5465570","wikidata":"https://www.wikidata.org/wiki/Q5326898","display_name":"Early stopping","level":3,"score":0.27489998936653137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2660999894142151},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.08367","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.08367","pdf_url":"https://arxiv.org/pdf/2611.08367","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2611.08367","doi":"https://doi.org/10.48550/arxiv.2611.08367","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.08367","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.08367","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.08367","pdf_url":"https://arxiv.org/pdf/2611.08367","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7163996727","https://openalex.org/W7221535475","https://openalex.org/W7171664955","https://openalex.org/W7166589956","https://openalex.org/W7161832508","https://openalex.org/W7134059465","https://openalex.org/W4416159353","https://openalex.org/W4399354026","https://openalex.org/W4416036761","https://openalex.org/W7160629695"],"abstract_inverted_index":{"Semantic":[0],"filtering":[1,96],"selects":[2],"records":[3,48,117],"that":[4,98],"satisfy":[5],"a":[6,70,93,104,123,147],"natural-language":[7],"predicate":[8],"and":[9,45,58,60,112,140,174,178,185,201,213],"is":[10],"an":[11,24,50,62,136],"important":[12],"operation":[13],"in":[14,146,217],"data":[15],"analytics":[16],"based":[17],"on":[18,27,109,162],"large":[19],"language":[20,106],"models":[21,44],"(LLMs).":[22],"Executing":[23],"expensive":[25],"model":[26,107],"every":[28],"document":[29,56],"incurs":[30],"substantial":[31],"inference":[32],"cost.":[33],"Existing":[34],"approaches":[35],"reduce":[36],"this":[37],"cost":[38,80,133],"by":[39,88],"accepting":[40],"predictions":[41],"from":[42],"cheaper":[43],"forwarding":[46],"uncertain":[47],"to":[49,119,135,165,181],"oracle.":[51,121,235],"Task":[52],"Cascades":[53],"further":[54,171],"varies":[55],"portions":[57],"operations,":[59],"provides":[61],"accuracy-guaranteed":[63],"extension.":[64],"However,":[65],"its":[66,194],"threshold":[67,128,163],"calibration":[68,152],"follows":[69],"prescribed":[71],"adjustment":[72],"sequence":[73],"after":[74,157],"cascade":[75,191],"assembly,":[76],"rather":[77],"than":[78],"minimizing":[79,131],"over":[81],"alternative":[82],"combinations":[83],"of":[84],"stage":[85],"thresholds.":[86],"Motivated":[87],"this,":[89],"we":[90,126],"propose":[91],"CascadeFilter,":[92],"three-stage":[94],"semantic":[95],"method":[97],"jointly":[99],"searches":[100],"the":[101,120,142,167,190,205,209,224,228,234],"thresholds":[102],"for":[103],"small":[105],"operating":[108,226],"extracted":[110],"evidence":[111,183],"full":[113],"documents,":[114],"with":[115,233],"unresolved":[116],"forwarded":[118],"For":[122],"fixed":[124],"cascade,":[125],"formulate":[127],"selection":[129],"as":[130],"token-aware":[132],"subject":[134],"oracle-relative":[137,155],"error":[138,156],"constraint,":[139],"select":[141],"least-cost":[143],"certified":[144],"configuration":[145],"pre-specified":[148],"grid.":[149],"A":[150],"finite-population":[151],"procedure":[153],"bounds":[154],"selection,":[158],"using":[159],"fixed-sequence":[160],"tests":[161],"tracks":[164],"allocate":[166],"multiple-testing":[168],"budget.":[169],"We":[170],"combine":[172],"lexical":[173],"dense":[175],"retrieval,":[176],"reranking,":[177],"neighborhood-supported":[179],"confidence":[180],"improve":[182],"extraction":[184],"routing.":[186],"These":[187,221],"components":[188],"enhance":[189],"while":[192],"leaving":[193],"certification":[195],"interface":[196],"unchanged.":[197],"Across":[198],"six":[199],"datasets":[200],"13":[202],"evaluation":[203],"settings,":[204],"reported":[206,225],"results":[207],"have":[208],"highest":[210],"benchmark":[211],"accuracy":[212,229],"macro-averaged":[214],"F1":[215],"score":[216],"12":[218],"settings":[219],"each.":[220],"comparisons":[222],"describe":[223],"points;":[227],"guarantee":[230],"concerns":[231],"agreement":[232]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-07T00:00:00"}