{"id":"https://openalex.org/W7152719532","doi":"https://doi.org/10.48550/arxiv.2604.06714","title":"Steering the Verifiability of Multimodal AI Hallucinations","display_name":"Steering the Verifiability of Multimodal AI Hallucinations","publication_year":2026,"publication_date":"2026-04-08","ids":{"openalex":"https://openalex.org/W7152719532","doi":"https://doi.org/10.48550/arxiv.2604.06714"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.06714","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06714","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.2604.06714","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133292042","display_name":"Jianhong Pang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pang, Jianhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133238128","display_name":"Ruoxi Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Ruoxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133267187","display_name":"Ziyi Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Ziyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133274968","display_name":"Xingjun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Xingjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123224035","display_name":"Zuxuan Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zuxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133305012","display_name":"Xuanjing Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Xuanjing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133263209","display_name":"Yu-Gang Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Yu-Gang","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5662999749183655,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5662999749183655,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.02669999934732914,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.025299999862909317,"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/categorization","display_name":"Categorization","score":0.5515999794006348},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5447999835014343},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.490200012922287},{"id":"https://openalex.org/keywords/psychological-intervention","display_name":"Psychological intervention","score":0.4796999990940094},{"id":"https://openalex.org/keywords/intervention","display_name":"Intervention (counseling)","score":0.46369999647140503},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.44940000772476196},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.3612000048160553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6233000159263611},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5515999794006348},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.5105000138282776},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.490200012922287},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.48590001463890076},{"id":"https://openalex.org/C27415008","wikidata":"https://www.wikidata.org/wiki/Q7256382","display_name":"Psychological intervention","level":2,"score":0.4796999990940094},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.46369999647140503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4514000117778778},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.44940000772476196},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3898000121116638},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.28279998898506165},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C3019207227","wikidata":"https://www.wikidata.org/wiki/Q10883614","display_name":"Human life","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2549999952316284},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.06714","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06714","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.2604.06714","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06714","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"AI":[0,54,72],"applications":[1,73],"driven":[2],"by":[3,33,108],"multimodal":[4,53],"large":[5],"language":[6],"models":[7],"(MLLMs)":[8],"are":[9,23,40],"prone":[10],"to":[11,17,67,92],"hallucinations":[12,22,55,94,98,133],"and":[13,77,95,101,124,131,154],"pose":[14],"considerable":[15],"risks":[16],"human":[18,34,90,109],"users.":[19,110],"Crucially,":[20],"such":[21],"not":[24],"equally":[25],"problematic:":[26],"some":[27],"hallucination":[28],"contents":[29],"could":[30],"be":[31],"detected":[32],"users(i.e.,":[35],"obvious":[36,100,123,130],"hallucinations),":[37],"while":[38],"others":[39],"often":[41],"missed":[42],"or":[43],"require":[44],"more":[45],"verification":[46],"effort(i.e.,":[47],"elusive":[48,102,125,132],"hallucinations).":[49],"This":[50],"indicates":[51],"that":[52,118,129,156],"vary":[56],"significantly":[57],"in":[58,162],"their":[59,106],"verifiability.":[60,145,165],"Yet,":[61],"little":[62],"research":[63],"has":[64],"explored":[65],"how":[66],"control":[68,141,173],"this":[69,82,152],"property":[70],"for":[71,122,139,178],"with":[74],"diverse":[75],"security":[76],"usability":[78],"demands.":[79],"To":[80],"address":[81],"gap,":[83],"we":[84,112],"construct":[85],"a":[86],"dataset":[87],"from":[88],"4,470":[89],"responses":[91],"AI-generated":[93],"categorize":[96],"these":[97,169],"into":[99],"types":[103],"based":[104],"on":[105],"verifiability":[107,176],"Further,":[111],"propose":[113],"an":[114],"activation-space":[115],"intervention":[116,136],"method":[117],"learns":[119],"separate":[120],"probes":[121],"hallucinations.":[126],"We":[127],"reveal":[128],"elicit":[134],"different":[135,179],"probes,":[137],"allowing":[138],"fine-grained":[140],"over":[142,174],"the":[143,149,175],"model's":[144],"Empirical":[146],"results":[147],"demonstrate":[148],"efficacy":[150],"of":[151],"approach":[153],"show":[155],"targeted":[157],"interventions":[158,170],"yield":[159],"superior":[160],"performance":[161],"regulating":[163],"corresponding":[164],"Moreover,":[166],"simply":[167],"mixing":[168],"enables":[171],"flexible":[172],"required":[177],"scenarios.":[180]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-10T00:00:00"}