{"id":"https://openalex.org/W4415795647","doi":"https://doi.org/10.52202/079017-3645","title":"Large language model validity via enhanced conformal prediction methods","display_name":"Large language model validity via enhanced conformal prediction methods","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415795647","doi":"https://doi.org/10.52202/079017-3645"},"language":"en","primary_location":{"id":"doi:10.52202/079017-3645","doi":"https://doi.org/10.52202/079017-3645","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-3645","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.09714","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086313752","display_name":"John J. Cherian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John Cherian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034642620","display_name":"Isaac Gibbs","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Isaac Gibbs","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5072495084","display_name":"Emmanuel J. Cand\u00e8s","orcid":"https://orcid.org/0000-0001-9234-924X","observed_orcids":["https://orcid.org/0000-0001-9234-924X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emmanuel Cand\u00e8s","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":6.8711,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.97692533,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"114812","last_page":"114842"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3174000084400177,"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":0.3174000084400177,"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":0.2110999971628189,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.14339999854564667,"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/conformal-prediction","display_name":"conformal prediction","score":0.9300000071525574},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9890000224113464},{"id":"https://openalex.org/keywords/split-conformal-prediction","display_name":"split conformal prediction","score":0.7770000100135803},{"id":"https://openalex.org/keywords/question-answering","display_name":"question answering","score":0.46700000762939453},{"id":"https://openalex.org/keywords/medical-question-answering","display_name":"medical question answering","score":0.5879999995231628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5669999718666077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4754999876022339},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3986999988555908},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28610000014305115},{"id":"https://openalex.org/C98214594","wikidata":"https://www.wikidata.org/wiki/Q850275","display_name":"Conformal map","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25540000200271606},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2526000142097473}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/079017-3645","doi":"https://doi.org/10.52202/079017-3645","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-3645","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.09714","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.09714","pdf_url":"https://arxiv.org/pdf/2406.09714","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.09714","doi":"https://doi.org/10.48550/arxiv.2406.09714","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.09714","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:2406.09714","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.09714","pdf_url":"https://arxiv.org/pdf/2406.09714","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G8401525520","display_name":"Collaborative Research: Transferable, Hierarchical, Expressive, Optimal, Robust, Interpretable Networks","funder_award_id":"2032014","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415795647.pdf","grobid_xml":"https://content.openalex.org/works/W4415795647.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2922110817","https://openalex.org/W4285429195","https://openalex.org/W4378942327","https://openalex.org/W4383987670","https://openalex.org/W4389519598","https://openalex.org/W4389520749","https://openalex.org/W4391988394","https://openalex.org/W4394652919","https://openalex.org/W4394868125","https://openalex.org/W4398230303","https://openalex.org/W4402683847","https://openalex.org/W4403813681","https://openalex.org/W4408178946","https://openalex.org/W4410803261","https://openalex.org/W4415796271","https://openalex.org/W4415798574"],"related_works":["https://openalex.org/W4381551003","https://openalex.org/W7204457146","https://openalex.org/W7154571449","https://openalex.org/W7127399149","https://openalex.org/W7154941992","https://openalex.org/W7155359046","https://openalex.org/W4391988394","https://openalex.org/W4415331743","https://openalex.org/W6948375827","https://openalex.org/W7172426478"],"abstract_inverted_index":{"We":[0,115,180],"develop":[1],"new":[2,123],"conformal":[3,21,64,124,131,178],"inference":[4],"methods":[5,38,67],"for":[6,173],"obtaining":[7],"validity":[8],"guarantees":[9,144],"on":[10,53,92,187],"the":[11,28,44,54,76,86,93,96,100,105,129,151,154,163,166,176,182],"output":[12],"of":[13,27,35,85,95,118,133,153,165,184],"large":[14],"language":[15,22],"models":[16],"(LLMs).":[17],"Prior":[18],"work":[19,39],"in":[20,68,138],"modeling":[23],"identifies":[24],"a":[25,32,49,59,170],"subset":[26],"text":[29],"that":[30],"satisfies":[31],"high-probability":[33],"guarantee":[34,77],"correctness.":[36],"These":[37],"by":[40],"filtering":[41,87,106],"claims":[42],"from":[43,72],"LLM's":[45],"original":[46],"response":[47],"if":[48],"scoring":[50,101,167],"function":[51,102,168],"evaluated":[52],"claim":[55],"fails":[56],"to":[57,140,149,160],"exceed":[58],"threshold":[60],"calibrated":[61],"via":[62,121,169],"split":[63],"prediction.":[65],"Existing":[66],"this":[69],"area":[70],"suffer":[71],"two":[73,122],"deficiencies.":[74],"First,":[75,126],"stated":[78],"is":[79,103],"not":[80],"conditionally":[81],"valid.":[82],"The":[83],"trustworthiness":[84],"step":[88,107],"may":[89],"vary":[90],"based":[91],"topic":[94],"response.":[97],"Second,":[98,156],"because":[99],"imperfect,":[104],"can":[108],"remove":[109],"many":[110],"valuable":[111],"and":[112,189],"accurate":[113],"claims.":[114],"address":[116],"both":[117],"these":[119],"challenges":[120],"methods.":[125],"we":[127,157],"generalize":[128],"conditional":[130,177],"procedure":[132],"Gibbs":[134],"et":[135],"al.":[136],"(2023)":[137],"order":[139],"adaptively":[141],"issue":[142],"weaker":[143],"when":[145],"they":[146],"are":[147],"required":[148],"preserve":[150],"utility":[152],"output.":[155],"show":[158],"how":[159],"systematically":[161],"improve":[162],"quality":[164],"novel":[171],"algorithm":[172],"differentiating":[174],"through":[175],"procedure.":[179],"demonstrate":[181],"efficacy":[183],"our":[185],"approach":[186],"biography":[188],"medical":[190],"question-answering":[191],"datasets.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":19},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":8}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-11-03T00:00:00"}