{"id":"https://openalex.org/W7160835305","doi":"https://doi.org/10.48550/arxiv.2605.08070","title":"VecCISC: Improving Confidence-Informed Self-Consistency with Reasoning Trace Clustering and Candidate Answer Selection","display_name":"VecCISC: Improving Confidence-Informed Self-Consistency with Reasoning Trace Clustering and Candidate Answer Selection","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160835305","doi":"https://doi.org/10.48550/arxiv.2605.08070"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.08070","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08070","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.08070","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135888678","display_name":"James Petullo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petullo, James","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135835309","display_name":"Sonny George","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George, Sonny","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033915638","display_name":"Dylan Cashman","orcid":"https://orcid.org/0000-0003-4853-5701"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cashman, Dylan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036715761","display_name":"Nianwen Xue","orcid":"https://orcid.org/0000-0002-4364-3618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Nianwen","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":0.6901000142097473,"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":0.6901000142097473,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.053199999034404755,"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":0.04600000008940697,"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/voting","display_name":"Voting","score":0.5285000205039978},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4952000081539154},{"id":"https://openalex.org/keywords/weighted-voting","display_name":"Weighted voting","score":0.47360000014305115},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.43560001254081726},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.43479999899864197},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.414900004863739},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.40310001373291016},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.3971000015735626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6428999900817871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5501999855041504},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.5285000205039978},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4952000081539154},{"id":"https://openalex.org/C132778050","wikidata":"https://www.wikidata.org/wiki/Q2065430","display_name":"Weighted voting","level":4,"score":0.47360000014305115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4645000100135803},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.43560001254081726},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.43479999899864197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42500001192092896},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C153668964","wikidata":"https://www.wikidata.org/wiki/Q27636","display_name":"Majority rule","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.375},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2635999917984009}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.08070","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08070","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.08070","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08070","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":"Preprint"},"sustainable_development_goals":[{"score":0.5772706270217896,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"A":[0],"standard":[1],"technique":[2],"for":[3],"scaling":[4],"inference-time":[5],"reasoning":[6,83,132],"is":[7,23],"Self-Consistency,":[8],"whereby":[9],"multiple":[10],"candidate":[11,47,148],"answers":[12,149],"are":[13,135],"sampled":[14],"from":[15],"an":[16],"LLM":[17,79,95],"and":[18,49,101,179],"the":[19,51,54,87,99,145,155,171,180,188,198],"most":[20],"common":[21],"answer":[22,48,52],"selected.":[24],"More":[25],"recently,":[26],"it":[27],"has":[28],"been":[29],"shown":[30],"that":[31,123,134,150,185],"weighted":[32,72,104],"majority":[33,73,105],"voting":[34,74],"(e.g.":[35],"Confidence-Informed":[36],"Self":[37],"Consistency":[38],"(CISC)),":[39],"which":[40],"assigns":[41],"a":[42,64,77,119,125],"confidence":[43,89],"value":[44],"to":[45,59,85,130,138],"each":[46,81],"chooses":[50],"with":[53],"largest":[55],"accumulated":[56],"score,":[57],"tends":[58],"be":[60,152],"more":[61],"accurate":[62],"on":[63,80,165],"wide":[65],"range":[66],"of":[67,94,103,127,147,173,200],"popular":[68],"benchmarks.":[69],"In":[70],"practice,":[71],"necessitates":[75],"calling":[76],"critic":[78],"candidate's":[82],"trace":[84],"produce":[86],"answer's":[88],"score.":[90],"This":[91],"secondary":[92],"series":[93],"calls":[96],"greatly":[97],"increases":[98],"overhead":[100],"cost":[102],"voting,":[106],"despite":[107],"its":[108],"potential":[109],"performance":[110],"benefits.":[111],"To":[112,157],"reduce":[113],"this":[114],"expense,":[115],"we":[116,162],"propose":[117],"VecCISC,":[118],"lightweight,":[120],"adaptive":[121],"framework":[122],"uses":[124],"measure":[126],"semantic":[128],"similarity":[129],"filter":[131],"traces":[133],"semantically":[136],"equivalent":[137],"others,":[139],"degenerate,":[140],"or":[141,196],"hallucinated,":[142],"thus":[143],"decreasing":[144],"number":[146],"must":[151],"evaluated":[153],"by":[154,192],"critic.":[156],"ensure":[158],"adequate":[159],"experimental":[160],"thoroughness,":[161],"evaluate":[163],"VecCISC":[164,186],"five":[166],"challenging,":[167],"widely-adopted":[168],"datasets":[169],"spanning":[170],"domains":[172],"mathematics,":[174],"chemistry,":[175],"biology,":[176],"commonsense":[177],"reasoning,":[178],"humanities.":[181],"Our":[182],"results":[183],"demonstrate":[184],"reduces":[187],"total":[189],"token":[190],"usage":[191],"47%,":[193],"while":[194],"maintaining":[195],"exceeding":[197],"accuracy":[199],"CISC.":[201]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-12T00:00:00"}