{"id":"https://openalex.org/W7140319546","doi":"https://doi.org/10.48550/arxiv.2603.22966","title":"Set-Valued Prediction for Large Language Models with Feasibility-Aware Coverage Guarantees","display_name":"Set-Valued Prediction for Large Language Models with Feasibility-Aware Coverage Guarantees","publication_year":2026,"publication_date":"2026-03-24","ids":{"openalex":"https://openalex.org/W7140319546","doi":"https://doi.org/10.48550/arxiv.2603.22966"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.22966","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.22966","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.2603.22966","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130559496","display_name":"Ye Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130608301","display_name":"Anqi Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Anqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130557191","display_name":"Yuanchang Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Yuanchang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041461882","display_name":"Shiyan Tong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong, Shiyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130613202","display_name":"Zhiyuan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130598764","display_name":"Bo Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Bo","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":0.3935999870300293,"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":0.3935999870300293,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.09799999743700027,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.0940999984741211,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.7085999846458435},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.6376000046730042},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.545799970626831},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4101000130176544},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.400299996137619},{"id":"https://openalex.org/keywords/point-estimation","display_name":"Point estimation","score":0.3693000078201294},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.3296000063419342}],"concepts":[{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.7085999846458435},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.651199996471405},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.6376000046730042},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.545799970626831},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4101000130176544},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3944999873638153},{"id":"https://openalex.org/C41426520","wikidata":"https://www.wikidata.org/wiki/Q1192065","display_name":"Point estimation","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3499000072479248},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3240000009536743},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2802000045776367},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2655999958515167},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C2992444157","wikidata":"https://www.wikidata.org/wiki/Q775079","display_name":"Single point","level":3,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.22966","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.22966","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.2603.22966","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.22966","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":{"Large":[0],"language":[1,196],"models":[2],"(LLMs)":[3],"inherently":[4],"operate":[5],"over":[6],"a":[7,22,69,76,84,135,156,169,178,182],"large":[8],"generation":[9,19,197],"space,":[10],"yet":[11],"conventional":[12],"usage":[13],"typically":[14],"reports":[15],"the":[16,27,31,43,66,99,126,174,186,204,208],"most":[17],"likely":[18],"(MLG)":[20],"as":[21],"point":[23,60],"prediction,":[24,64,89],"which":[25,90,142],"underestimates":[26],"model's":[28],"capability:":[29],"although":[30],"top-ranked":[32],"response":[33,121],"can":[34,48],"be":[35,50,147],"incorrect,":[36],"valid":[37],"answers":[38],"may":[39,115],"still":[40],"exist":[41],"within":[42,125],"broader":[44],"output":[45],"space":[46],"and":[47,207],"potentially":[49],"discovered":[51],"through":[52],"repeated":[53],"sampling.":[54],"This":[55],"observation":[56],"motivates":[57],"moving":[58],"from":[59,164],"prediction":[61,162],"to":[62,117],"set-valued":[63,88],"where":[65],"model":[67],"produces":[68],"set":[70,176],"of":[71,102,211],"candidate":[72,128],"responses":[73,166],"rather":[74],"than":[75],"single":[77],"MLG.":[78],"In":[79],"this":[80,151],"paper,":[81],"we":[82,133,153],"propose":[83],"principled":[85],"framework":[86],"for":[87,122],"provides":[91],"feasibility-aware":[92],"coverage":[93,105,144],"guarantees.":[94],"We":[95],"show":[96],"that,":[97],"given":[98],"finite-sampling":[100],"nature":[101],"LLM":[103],"generation,":[104],"is":[106,190],"not":[107],"always":[108],"achievable:":[109],"even":[110],"with":[111,181,199],"multiple":[112],"samplings,":[113],"LLMs":[114,201],"fail":[116],"yield":[118],"an":[119],"acceptable":[120],"certain":[123],"questions":[124],"sampled":[127,165],"set.":[129],"To":[130],"address":[131],"this,":[132],"establish":[134],"minimum":[136],"achievable":[137],"risk":[138,188],"level":[139,189],"(MRL),":[140],"below":[141],"statistical":[143,205],"guarantees":[145],"cannot":[146],"satisfied.":[148],"Building":[149],"on":[150,194],"insight,":[152],"then":[154],"develop":[155],"data-driven":[157],"calibration":[158],"procedure":[159],"that":[160,173],"constructs":[161],"sets":[163],"by":[167],"estimating":[168],"rigorous":[170],"threshold,":[171],"ensuring":[172],"resulting":[175],"contains":[177],"correct":[179],"answer":[180],"desired":[183],"probability":[184],"whenever":[185],"target":[187],"feasible.":[191],"Extensive":[192],"experiments":[193],"six":[195],"tasks":[198],"five":[200],"demonstrate":[202],"both":[203],"validity":[206],"predictive":[209],"efficiency":[210],"our":[212],"framework.":[213]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-26T00:00:00"}