{"id":"https://openalex.org/W7222944591","doi":"https://doi.org/10.48550/arxiv.2610.23527","title":"Truth in Contrast: Calibrated Factual Evidence from Language Model Likelihoods","display_name":"Truth in Contrast: Calibrated Factual Evidence from Language Model Likelihoods","publication_year":2026,"publication_date":"2026-10-16","ids":{"openalex":"https://openalex.org/W7222944591","doi":"https://doi.org/10.48550/arxiv.2610.23527"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.23527","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.23527","pdf_url":"https://arxiv.org/pdf/2610.23527","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.23527","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106011068","display_name":"Ponhvoan Srey","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Srey, Ponhvoan","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060378653","display_name":"Jason Samuel Lucas","orcid":"https://orcid.org/0009-0000-3494-6935","observed_orcids":["https://orcid.org/0009-0000-3494-6935"]},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lucas, Jason","raw_affiliation_strings":["University of Colorado at Boulder"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colorado at Boulder","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088392357","display_name":"Pittawat Taveekitworachai","orcid":"https://orcid.org/0000-0002-6824-2634","observed_orcids":["https://orcid.org/0000-0002-6824-2634"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Taveekitworachai, Pittawat","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159083033","display_name":"Junyoung Lee","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lee, Junyoung","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050386762","display_name":"Anh Tuan Luu","orcid":"https://orcid.org/0000-0001-6062-207X","observed_orcids":["https://orcid.org/0000-0001-6062-207X"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I4210142044","display_name":"VinUniversity","ror":"https://ror.org/052dmdr17","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210142044"]}],"countries":["SG","VN"],"is_corresponding":false,"raw_author_name":"Luu, Anh Tuan","raw_affiliation_strings":["Nanyang Technological University","VinUniversity"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"VinUniversity","institution_ids":["https://openalex.org/I4210142044"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.9409000277519226,"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":0.9409000277519226,"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":0.03840000182390213,"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":0.00559999980032444,"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/large-language-models","display_name":"large language models","score":0.7829999923706055},{"id":"https://openalex.org/keywords/calibration","display_name":"calibration","score":0.6819999814033508},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8669999837875366}],"concepts":[{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6877999901771545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5947999954223633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5644000172615051},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5540000200271606},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5182999968528748},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C2779525943","wikidata":"https://www.wikidata.org/wiki/Q1187300","display_name":"Grammaticality","level":3,"score":0.4049000144004822},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3937000036239624},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.38109999895095825},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3540000021457672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34929999709129333},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C153578388","wikidata":"https://www.wikidata.org/wiki/Q351625","display_name":"Theoretical linguistics","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.319599986076355},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3100000023841858},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C2777629044","wikidata":"https://www.wikidata.org/wiki/Q614959","display_name":"Contrastive analysis","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2840000092983246},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.27880001068115234},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26589998602867126},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.25380000472068787}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.23527","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.23527","pdf_url":"https://arxiv.org/pdf/2610.23527","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.2610.23527","doi":"https://doi.org/10.48550/arxiv.2610.23527","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.23527","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.23527","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.23527","pdf_url":"https://arxiv.org/pdf/2610.23527","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7222944591.pdf","grobid_xml":"https://content.openalex.org/works/W7222944591.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4404792985","https://openalex.org/W7204191336","https://openalex.org/W4412377043","https://openalex.org/W4414037079","https://openalex.org/W4388717471","https://openalex.org/W7118582830","https://openalex.org/W3162385798","https://openalex.org/W4391988394","https://openalex.org/W7161773685","https://openalex.org/W7212364591"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"encode":[4],"substantial":[5],"factual":[6,12,20,32,55,104,172],"knowledge.":[7],"Yet,":[8],"estimating":[9],"confidence":[10,21],"in":[11,118],"claims":[13,158],"reliably":[14],"remains":[15],"challenging.":[16],"We":[17,69],"study":[18],"likelihood-based":[19],"from":[22],"the":[23,47,50,64,77,81,124,127,165],"complementary":[24],"perspectives":[25],"of":[26,49,126],"discrimination":[27,105,112,169],"and":[28,56,59,92,170],"calibration":[29,74,95,101],"across":[30,88,116],"multilingual":[31],"statements.":[33],"Specifically,":[34],"we":[35,133,154],"instantiate":[36],"contrastive":[37],"generative":[38],"likelihoods":[39],"as":[40],"Contrastive":[41,65],"Factual":[42,66],"Evidence":[43],"(CFE),":[44],"which":[45,121,139],"compares":[46],"likelihood":[48,136],"same":[51],"claim":[52],"under":[53],"competing":[54],"non-factual":[57],"conditions,":[58],"derive":[60],"its":[61,108],"probabilistic":[62],"counterpart,":[63],"Posterior":[67],"(CFP).":[68],"show":[70],"analytically":[71],"that":[72],"CFP":[73,98],"depends":[75],"on":[76],"differential":[78],"error":[79],"between":[80],"two":[82],"surrogate":[83],"conditionals,":[84],"allowing":[85],"errors":[86],"shared":[87],"them":[89],"to":[90,107],"cancel":[91],"yield":[93],"tighter":[94],"bounds.":[96],"Empirically,":[97],"substantially":[99],"improves":[100],"while":[102],"maintaining":[103],"comparable":[106],"strongest":[109],"competitor.":[110],"Nonetheless,":[111],"is":[113,143],"uniformly":[114],"weak":[115],"methods":[117],"lower-resource":[119],"languages,":[120],"simultaneously":[122],"undermines":[123],"utility":[125],"measured":[128],"calibration.":[129],"To":[130],"this":[131],"end,":[132],"interpret":[134],"a":[135],"geometry,":[137],"within":[138],"an":[140,147],"evidence-bearing":[141],"direction":[142],"induced,":[144],"along":[145,164],"with":[146,159],"orthogonal":[148],"evidence-invariant":[149],"direction.":[150],"In":[151],"our":[152],"investigation,":[153],"selectively":[155],"align":[156],"target-language":[157,175],"stronger":[160],"English":[161],"evidence":[162],"only":[163],"factual-evidence":[166],"direction,":[167],"improving":[168],"open-ended":[171],"generation":[173],"without":[174],"labels.":[176]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-20T00:00:00"}