{"id":"https://openalex.org/W7137962370","doi":"https://doi.org/10.1609/aaai.v40i36.40254","title":"Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions","display_name":"Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137962370","doi":"https://doi.org/10.1609/aaai.v40i36.40254"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i36.40254","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i36.40254","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40254/44215","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40254/44215","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070125882","display_name":"Guy Bar-Shalom","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Guy Bar-Shalom","raw_affiliation_strings":["Technion"],"affiliations":[{"raw_affiliation_string":"Technion","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029627909","display_name":"Fabrizio Frasca","orcid":"https://orcid.org/0000-0002-5165-1394"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Fabrizio Frasca","raw_affiliation_strings":["Technion"],"affiliations":[{"raw_affiliation_string":"Technion","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079620830","display_name":"Derek Lim","orcid":"https://orcid.org/0000-0001-8408-9484"},"institutions":[{"id":"https://openalex.org/I2799848540","display_name":"Center for Open Science","ror":"https://ror.org/05d5mza29","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2799848540"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Derek Lim","raw_affiliation_strings":["Open AI\nMIT"],"affiliations":[{"raw_affiliation_string":"Open AI\nMIT","institution_ids":["https://openalex.org/I2799848540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129672678","display_name":"Yoav Gelberg","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]},{"id":"https://openalex.org/I4210136001","display_name":"Oxford Centre for Mission Studies","ror":"https://ror.org/040059s22","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210136001"]}],"countries":["GB","IL"],"is_corresponding":false,"raw_author_name":"Yoav Gelberg","raw_affiliation_strings":["Technion\nOxford"],"affiliations":[{"raw_affiliation_string":"Technion\nOxford","institution_ids":["https://openalex.org/I4210136001","https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003744048","display_name":"Yftah Ziser","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["GB","NL"],"is_corresponding":false,"raw_author_name":"Yftah Ziser","raw_affiliation_strings":["University of Groningen\nNvidia"],"affiliations":[{"raw_affiliation_string":"University of Groningen\nNvidia","institution_ids":["https://openalex.org/I1304085615","https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129651213","display_name":"Ran El-Yaniv","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Ran El-Yaniv","raw_affiliation_strings":["Technion\nNvidia"],"affiliations":[{"raw_affiliation_string":"Technion\nNvidia","institution_ids":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045719865","display_name":"Gal Chechik","orcid":"https://orcid.org/0000-0001-9164-5303"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["GB","IL"],"is_corresponding":false,"raw_author_name":"Gal Chechik","raw_affiliation_strings":["Bar Ilan Universit\nNvidia"],"affiliations":[{"raw_affiliation_string":"Bar Ilan Universit\nNvidia","institution_ids":["https://openalex.org/I1304085615","https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129670537","display_name":"Haggai Maron","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Haggai Maron","raw_affiliation_strings":["Technion\nNvidia"],"affiliations":[{"raw_affiliation_string":"Technion\nNvidia","institution_ids":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5070125882"],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17373939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"36","first_page":"30058","last_page":"30066"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.15049999952316284,"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":0.15049999952316284,"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/T12488","display_name":"Mental Health via Writing","score":0.0568000003695488,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.05420000106096268,"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/leverage","display_name":"Leverage (statistics)","score":0.6563000082969666},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5254999995231628},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45669999718666077},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4560000002384186},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4108000099658966},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.3959999978542328},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3765999972820282},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.37220001220703125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8102999925613403},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6563000082969666},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5254999995231628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4927999973297119},{"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/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4560000002384186},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4352000057697296},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3222000002861023},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i36.40254","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i36.40254","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40254/44215","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i36.40254","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i36.40254","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40254/44215","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.45293906331062317}],"awards":[{"id":"https://openalex.org/G5670947113","display_name":"EPSRC Centre for Doctoral Training in Autonomous Intelligent Machines and Systems","funder_award_id":"EP/S024050/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137962370.pdf","grobid_xml":"https://content.openalex.org/works/W7137962370.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"automated":[1],"detection":[2,172],"of":[3,15,45,66,86,92,100,142,152],"hallucinations":[4,123],"and":[5,113,124,166,182],"training":[6],"data":[7,119,125],"contamination":[8],"is":[9,33],"pivotal":[10],"to":[11,30,72,105],"the":[12,43,49,59,63,82,97,108,143],"safe":[13],"deployment":[14],"Large":[16],"Language":[17],"Models":[18],"(LLMs).":[19],"These":[20],"tasks":[21],"are":[22],"particularly":[23],"challenging":[24],"in":[25,37,48,62],"settings":[26],"where":[27],"no":[28],"access":[29],"model":[31],"internals":[32],"available.":[34],"Current":[35],"approaches":[36],"this":[38,106],"setup":[39],"typically":[40],"leverage":[41],"only":[42,91],"probabilities":[44],"actual":[46],"tokens":[47],"text,":[50],"relying":[51],"on":[52,138],"simple":[53],"task-specific":[54],"heuristics.":[55],"Crucially,":[56],"they":[57],"overlook":[58],"information":[60],"contained":[61],"full":[64,98],"sequence":[65,99],"next-token":[67,93,101],"probability":[68],"distributions.":[69,102],"We":[70,103],"propose":[71],"go":[73],"beyond":[74],"hand-crafted":[75],"decision":[76],"rules":[77],"by":[78],"learning":[79],"directly":[80],"from":[81],"complete":[83],"observable":[84],"output":[85],"LLMs":[87],"\u2014":[88],"consisting":[89],"not":[90],"probabilities,":[94],"but":[95],"also":[96],"refer":[104],"as":[107,116],"LLM":[109],"Output":[110],"Signature":[111],"(LOS),":[112],"treat":[114],"it":[115,175],"a":[117,133,149],"reference":[118],"type":[120],"for":[121,155],"detecting":[122],"contamination.":[126],"To":[127],"that":[128],"end,":[129],"we":[130],"introduce":[131],"LOS-Net,":[132],"lightweight":[134],"attention-based":[135],"architecture":[136],"trained":[137],"an":[139],"efficient":[140],"encoding":[141],"LOS,":[144],"which":[145],"can":[146],"provably":[147],"approximate":[148],"broad":[150],"class":[151],"existing":[153],"techniques":[154],"both":[156],"tasks.":[157],"Empirically,":[158],"LOS-Net":[159],"achieves":[160],"superior":[161],"performance":[162],"across":[163,180],"diverse":[164],"benchmarks":[165],"LLMs,":[167],"while":[168],"maintaining":[169],"extremely":[170],"low":[171],"latency.":[173],"Furthermore,":[174],"demonstrates":[176],"promising":[177],"transfer":[178],"capabilities":[179],"datasets":[181],"LLMs.":[183]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-03-18T00:00:00"}