{"id":"https://openalex.org/W7140145192","doi":"https://doi.org/10.18653/v1/2026.fever-1.4","title":"The Energy of Falsehood: Detecting Hallucinations via Diffusion Model Likelihoods","display_name":"The Energy of Falsehood: Detecting Hallucinations via Diffusion Model Likelihoods","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140145192","doi":"https://doi.org/10.18653/v1/2026.fever-1.4"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.fever-1.4","doi":"https://doi.org/10.18653/v1/2026.fever-1.4","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.fever-1.4","pdf_url":"https://aclanthology.org/2026.fever-1.4.pdf","source":{"id":"https://openalex.org/S7407105028","display_name":"Fact Extraction and VERification Workshop (FEVER)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth Fact Extraction and VERification Workshop (FEVER)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.fever-1.4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091549332","display_name":"Arpit Singh Gautam","orcid":"https://orcid.org/0009-0005-8964-4340","observed_orcids":["https://orcid.org/0009-0005-8964-4340"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arpit Singh Gautam","raw_affiliation_strings":["Dell Technologies , CSG CTO Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dell Technologies , CSG CTO Team","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125912224","display_name":"Kailash Talreja","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kailash Talreja","raw_affiliation_strings":["Dell Technologies , CSG CTO Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dell Technologies , CSG CTO Team","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134402504","display_name":"Saurabh Jha","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saurabh Jha","raw_affiliation_strings":["Dell Technologies , CSG CTO Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dell Technologies , CSG CTO Team","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6139,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90022931,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"47","last_page":"58"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5214999914169312,"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":0.5214999914169312,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.4207000136375427,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.024299999698996544,"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/hallucination-detection","display_name":"hallucination detection","score":0.9589999914169312},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9559999704360962},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.7329999804496765},{"id":"https://openalex.org/keywords/non-equilibrium-thermodynamics","display_name":"non-equilibrium thermodynamics","score":0.7889999747276306},{"id":"https://openalex.org/keywords/confidence-calibration","display_name":"confidence calibration","score":0.6380000114440918},{"id":"https://openalex.org/keywords/fact-checking","display_name":"fact-checking","score":0.8009999990463257},{"id":"https://openalex.org/keywords/unsupervised-detection","display_name":"unsupervised detection","score":0.4909999966621399},{"id":"https://openalex.org/keywords/zero-shot-generalization","display_name":"zero-shot generalization","score":0.6539999842643738},{"id":"https://openalex.org/keywords/fever","display_name":"fever","score":0.5849999785423279},{"id":"https://openalex.org/keywords/hovering","display_name":"hover","score":0.9309999942779541}],"concepts":[{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5177000164985657},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.450300008058548},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.3714999854564667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3644999861717224},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.35989999771118164},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3230000138282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29820001125335693},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27459999918937683}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.fever-1.4","doi":"https://doi.org/10.18653/v1/2026.fever-1.4","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.fever-1.4","pdf_url":"https://aclanthology.org/2026.fever-1.4.pdf","source":{"id":"https://openalex.org/S7407105028","display_name":"Fact Extraction and VERification Workshop (FEVER)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth Fact Extraction and VERification Workshop (FEVER)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2602.11364","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.11364","pdf_url":"https://arxiv.org/pdf/2602.11364","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.2602.11364","doi":"https://doi.org/10.48550/arxiv.2602.11364","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.11364","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":"doi:10.18653/v1/2026.fever-1.4","doi":"https://doi.org/10.18653/v1/2026.fever-1.4","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.fever-1.4","pdf_url":"https://aclanthology.org/2026.fever-1.4.pdf","source":{"id":"https://openalex.org/S7407105028","display_name":"Fact Extraction and VERification Workshop (FEVER)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth Fact Extraction and VERification Workshop (FEVER)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140145192.pdf","grobid_xml":"https://content.openalex.org/works/W7140145192.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2965373594","https://openalex.org/W3119800657","https://openalex.org/W4285429195","https://openalex.org/W4310421098","https://openalex.org/W4321594373","https://openalex.org/W4327810158","https://openalex.org/W4361012985","https://openalex.org/W4383987670","https://openalex.org/W4389519449","https://openalex.org/W4389520333","https://openalex.org/W4389984066","https://openalex.org/W4401042773","https://openalex.org/W4412158322"],"related_works":["https://openalex.org/W4392617635","https://openalex.org/W7127381609","https://openalex.org/W7139029953","https://openalex.org/W4403223051","https://openalex.org/W4412404236","https://openalex.org/W7207592016","https://openalex.org/W4413423557","https://openalex.org/W4416374261","https://openalex.org/W7201835280","https://openalex.org/W4417101246"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"frequently":[4],"\"hallucinate\"":[5],"plausible":[6],"but":[7],"incorrect":[8],"assertions,":[9],"a":[10,43,63,71,98,114],"vulnerability":[11],"often":[12],"missed":[13],"by":[14,122,142],"uncertainty":[15],"metrics":[16],"when":[17],"models":[18],"are":[19,48,56],"\"confidently":[20],"wrong.\"We":[21],"propose":[22,97],"DiffuTruth,":[23],"an":[24,85],"unsupervised":[25,116],"framework":[26],"that":[27,35],"re-conceptualizes":[28],"fact":[29],"verification":[30],"via":[31],"non-equilibrium":[32],"thermodynamics,":[33],"positing":[34],"factual":[36,94],"truths":[37],"act":[38],"as":[39],"stable":[40],"attractors":[41],"on":[42,109,135],"generative":[44],"manifold":[45],"while":[46],"hallucinations":[47],"unstable.We":[49],"introduce":[50],"the":[51,74,78,125,136,146],"\"Generative":[52],"Stress":[53],"Test\":":[54],"claims":[55],"corrupted":[57],"with":[58,105],"noise":[59],"and":[60,81],"reconstructed":[61],"using":[62,84],"discrete":[64],"text":[65],"diffusion":[66],"model.We":[67],"define":[68],"Semantic":[69,90],"Energy,":[70],"metric":[72],"measuring":[73],"semantic":[75],"divergence":[76],"between":[77],"original":[79],"claim":[80],"its":[82],"reconstruction":[83],"NLI":[86],"critic.Unlike":[87],"vector-space":[88],"errors,":[89],"Energy":[91],"isolates":[92],"deep":[93],"contradictions.We":[95],"further":[96],"Hybrid":[99],"Calibration":[100],"fusing":[101],"this":[102],"stability":[103],"signal":[104],"discriminative":[106],"confidence.Extensive":[107],"experiments":[108],"FEVER":[110],"demonstrate":[111],"DiffuTruth":[112],"achieves":[113],"state-of-theart":[115],"AUROC":[117],"of":[118,127,148],"0.725,":[119],"outperforming":[120,140],"baselines":[121,141],"+1.5%":[123],"through":[124],"correction":[126],"overconfident":[128],"predictions.Furthermore,":[129],"we":[130],"show":[131],"superior":[132],"zero-shot":[133],"generalization":[134],"multi-hop":[137],"HOVER":[138],"dataset,":[139],"over":[143],"4%,":[144],"confirming":[145],"robustness":[147],"thermodynamic":[149],"truth":[150],"properties":[151],"to":[152],"distribution":[153],"shifts.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-02-16T00:00:00"}