{"id":"https://openalex.org/W4416040343","doi":"https://doi.org/10.1109/iccv51701.2025.00692","title":"TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination via Latent Truthful-Guided Pre-Intervention","display_name":"TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination via Latent Truthful-Guided Pre-Intervention","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416040343","doi":"https://doi.org/10.1109/iccv51701.2025.00692"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.10602","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jinhao Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinhao Duan","raw_affiliation_strings":["Drexel University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Drexel University","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078913688","display_name":"Fei Kong","orcid":"https://orcid.org/0000-0003-0999-1501"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Kong","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406787","display_name":"Hao Cheng","orcid":"https://orcid.org/0000-0002-3254-4796"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Cheng","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078914868","display_name":"James Diffenderfer","orcid":"https://orcid.org/0009-0004-8641-3275"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Diffenderfer","raw_affiliation_strings":["LLNL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LLNL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041470575","display_name":"Bhavya Kailkhura","orcid":"https://orcid.org/0000-0002-2819-2919"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhavya Kailkhura","raw_affiliation_strings":["LLNL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LLNL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015105117","display_name":"Lichao Sun","orcid":"https://orcid.org/0000-0003-1539-7939"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lichao Sun","raw_affiliation_strings":["Lehigh University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehigh University","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019106292","display_name":"Xiaofeng Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Zhu","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069008709","display_name":"Xiaoshuang Shi","orcid":"https://orcid.org/0000-0003-4934-0850"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuang Shi","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102775611","display_name":"Kaidi Xu","orcid":"https://orcid.org/0000-0003-4437-0671"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaidi Xu","raw_affiliation_strings":["Drexel University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Drexel University","institution_ids":["https://openalex.org/I72816309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15842014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7372","last_page":"7382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.36880001425743103,"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":0.36880001425743103,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.07069999724626541,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.057100001722574234,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6797000169754028},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.616599977016449},{"id":"https://openalex.org/keywords/transferability","display_name":"Transferability","score":0.4781000018119812},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4449999928474426},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.43230000138282776},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.4316999912261963},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.40939998626708984},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3828999996185303}],"concepts":[{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6797000169754028},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6197999715805054},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.616599977016449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5929999947547913},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.4781000018119812},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3447999954223633},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.33719998598098755},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3336000144481659},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.272599995136261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2662000060081482},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2563999891281128},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv51701.2025.00692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.10602","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10602","pdf_url":"https://arxiv.org/pdf/2503.10602","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"pmh:doi:10.48550/arxiv.2503.10602","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2503.10602","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.10602","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.10602","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10602","pdf_url":"https://arxiv.org/pdf/2503.10602","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Object":[0],"Hallucination":[1],"(OH)":[2],"has":[3],"been":[4],"acknowledged":[5],"as":[6,30,55],"one":[7],"of":[8,37,74,92,102,134],"the":[9,34,131],"major":[10],"trustworthy":[11],"challenges":[12],"in":[13,20,47,104,169],"Large":[14,21],"Vision-Language":[15],"Models":[16,23],"(LVLMs).":[17],"Recent":[18],"advancements":[19],"Language":[22],"(LLMs)":[24],"indicate":[25,186],"that":[26,83,109,128,187],"internal":[27,45,76,86],"states,":[28,32],"such":[29],"hidden":[31],"encode":[33,99],"\"overall":[35],"truthfulness\"":[36],"generated":[38],"responses.":[39],"However,":[40],"it":[41],"remains":[42],"under-explored":[43],"how":[44],"states":[46,77,87],"LVLMs":[48,98,180],"function":[49],"and":[50,81,137,154,161,175,181],"whether":[51],"they":[52],"could":[53],"serve":[54],"\"per-token\"":[56],"hallucination":[57,93,156,163],"indicators,":[58],"which":[59],"is":[60],"essential":[61],"for":[62],"mitigating":[63],"OH.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68,123],"first":[69,129],"conduct":[70],"an":[71],"in-depth":[72],"exploration":[73],"LVLM":[75,85,135,144],"with":[78],"OH":[79,182],"issues":[80],"discover":[82],"(1)":[84],"are":[88],"high-specificity":[89],"per-token":[90],"indicators":[91],"behaviors.":[94],"Moreover,":[95],"(2)":[96],"different":[97],"universal":[100],"patterns":[101],"hallucinations":[103],"common":[105],"latent":[106,164],"subspaces,":[107],"indicating":[108],"there":[110],"exist":[111],"\"generic":[112],"truthful":[113,132],"directions\"":[114],"shared":[115],"by":[116,159],"various":[117],"LVLMs.":[118],"Based":[119],"on":[120],"these":[121],"discoveries,":[122],"propose":[124,148],"Truthful-Guided":[125],"Pre-Intervention":[126],"(TruthPrInt)":[127],"learns":[130],"direction":[133],"decoding":[136],"then":[138],"applies":[139],"truthful-guided":[140],"inference-time":[141],"intervention":[142],"during":[143],"decoding.":[145],"We":[146,166],"further":[147],"TruthPrInt":[149,168,188],"to":[150],"enhance":[151],"both":[152],"cross-LVLM":[153],"cross-data":[155],"detection":[157],"transferability":[158],"constructing":[160],"aligning":[162],"subspaces.":[165],"evaluate":[167],"extensive":[170],"experimental":[171],"settings,":[172],"including":[173],"in-domain":[174],"out-of-domain":[176],"scenarios,":[177],"over":[178],"popular":[179],"benchmarks.":[183],"Experimental":[184],"results":[185],"significantly":[189],"outperforms":[190],"state-of-the-art":[191],"methods.":[192],"Codes":[193],"will":[194],"be":[195],"available":[196],"at":[197],"https://github.com/jinhaoduan/TruthPrInt.":[198]},"counts_by_year":[],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}