{"id":"https://openalex.org/W4415539341","doi":"https://doi.org/10.1145/3746027.3755118","title":"DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models","display_name":"DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539341","doi":"https://doi.org/10.1145/3746027.3755118"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755118","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755118","pdf_url":null,"source":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755118","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101732442","display_name":"Yudong Zhang","orcid":"https://orcid.org/0009-0009-6049-603X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yudong Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China and Tencent, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-6049-603X","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China and Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101577090","display_name":"Ruobing Xie","orcid":"https://orcid.org/0000-0003-3170-5647"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruobing Xie","raw_affiliation_strings":["Tencent, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3170-5647","affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039337290","display_name":"Xingwu Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingwu Sun","raw_affiliation_strings":["Tencent, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-3222-0901","affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058825605","display_name":"Yiqing Huang","orcid":"https://orcid.org/0000-0002-2143-3329"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqing Huang","raw_affiliation_strings":["Tencent, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2143-3329","affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668653","display_name":"Jiansheng Chen","orcid":"https://orcid.org/0000-0002-2040-7938"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiansheng Chen","raw_affiliation_strings":["University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2040-7938","affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020128898","display_name":"Zhanhui Kang","orcid":"https://orcid.org/0009-0006-5151-4222"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanhui Kang","raw_affiliation_strings":["Tencent, Shenzhen, Guandong, China"],"raw_orcid":"https://orcid.org/0009-0006-5151-4222","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, Guandong, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Di Wang","orcid":"https://orcid.org/0009-0003-6713-1638"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Wang","raw_affiliation_strings":["Tencent, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-6713-1638","affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100445061","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-6108-5157"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6108-5157","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3555","last_page":"3564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10241","display_name":"Functional Brain Connectivity Studies","score":0.9782999753952026,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.972599983215332,"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/identification","display_name":"Identification (biology)","score":0.5519000291824341},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.544700026512146},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5367000102996826},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3619999885559082},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3594000041484833},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3531000018119812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5755000114440918},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5519000291824341},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.544700026512146},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5367000102996826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46239998936653137},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4235000014305115},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.41679999232292175},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3531000018119812},{"id":"https://openalex.org/C26876914","wikidata":"https://www.wikidata.org/wiki/Q11166","display_name":"Dynamic Host Configuration Protocol","level":3,"score":0.3142000138759613},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29760000109672546},{"id":"https://openalex.org/C2779727114","wikidata":"https://www.wikidata.org/wiki/Q170082","display_name":"Psychosis","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C2776706361","wikidata":"https://www.wikidata.org/wiki/Q1054088","display_name":"Auditory hallucination","level":3,"score":0.25999999046325684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755118","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755118","pdf_url":null,"source":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755118","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755118","pdf_url":null,"source":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3464219606","display_name":null,"funder_award_id":"62376024, 62325405, 62104128, 62203257, 62031017, 62406159, U21B2031","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W4380995299","https://openalex.org/W4393160204","https://openalex.org/W4399803256","https://openalex.org/W4402670231","https://openalex.org/W4403617527","https://openalex.org/W4409363177"],"related_works":[],"abstract_inverted_index":{"Large":[0],"vision-language":[1],"models":[2],"(LVLMs)":[3],"have":[4],"demonstrated":[5],"exceptional":[6],"performance":[7,88],"on":[8],"complex":[9],"multimodal":[10],"tasks.":[11],"However,":[12],"they":[13],"continue":[14],"to":[15,107],"suffer":[16],"from":[17],"significant":[18],"hallucination":[19,41,90],"issues,":[20],"including":[21],"object,":[22],"attribute,":[23],"and":[24,42,69,99,111],"relational":[25],"hallucinations.":[26,56],"To":[27],"accurately":[28],"detect":[29],"these":[30,46,114],"hallucinations,":[31],"we":[32,48],"investigated":[33],"the":[34,97,109],"variations":[35],"in":[36,89,103],"cross-modal":[37],"attention":[38],"patterns":[39],"between":[40],"non-hallucination":[43],"states.":[44],"Leveraging":[45],"distinctions,":[47],"developed":[49],"a":[50],"lightweight":[51],"detector":[52],"capable":[53],"of":[54,101,113],"identifying":[55],"Our":[57],"proposed":[58],"method,":[59],"Detecting":[60],"Hallucinations":[61],"by":[62],"Cross-modal":[63],"Attention":[64],"Patterns":[65],"(DHCP),":[66],"is":[67,118],"straightforward":[68],"does":[70],"not":[71],"require":[72],"additional":[73],"LVLM":[74,78],"training":[75],"or":[76],"extra":[77],"inference":[79],"steps.":[80],"Experimental":[81],"results":[82],"show":[83],"that":[84],"DHCP":[85,105],"achieves":[86],"remarkable":[87],"detection.":[91],"By":[92],"offering":[93],"novel":[94],"insights":[95],"into":[96],"identification":[98],"analysis":[100],"hallucinations":[102],"LVLMs,":[104],"contributes":[106],"advancing":[108],"reliability":[110],"trustworthiness":[112],"models.":[115],"The":[116],"code":[117],"available":[119],"at":[120],"https://github.com/btzyd/DHCP.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-25T00:00:00"}
