{"id":"https://openalex.org/W7147637564","doi":"https://doi.org/10.1109/cnml68938.2026.11453286","title":"Low-Cost Verification for Multimodal Large Language Models","display_name":"Low-Cost Verification for Multimodal Large Language Models","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7147637564","doi":"https://doi.org/10.1109/cnml68938.2026.11453286"},"language":null,"primary_location":{"id":"doi:10.1109/cnml68938.2026.11453286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11453286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102909930","display_name":"Siwen Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I88830068","display_name":"Shaanxi Normal University","ror":"https://ror.org/0170z8493","country_code":"CN","type":"education","lineage":["https://openalex.org/I88830068"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shunhong Zhang","raw_affiliation_strings":["Shaanxi Normal University,School of Artificial Intelligence and Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Normal University,School of Artificial Intelligence and Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I88830068"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057444662","display_name":"Gang L\u00fc","orcid":"https://orcid.org/0000-0001-5921-1839"},"institutions":[{"id":"https://openalex.org/I88830068","display_name":"Shaanxi Normal University","ror":"https://ror.org/0170z8493","country_code":"CN","type":"education","lineage":["https://openalex.org/I88830068"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Lu","raw_affiliation_strings":["Shaanxi Normal University,School of Artificial Intelligence and Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Normal University,School of Artificial Intelligence and Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I88830068"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017875810","display_name":"Zichen Ma","orcid":"https://orcid.org/0000-0001-5748-1675"},"institutions":[{"id":"https://openalex.org/I88830068","display_name":"Shaanxi Normal University","ror":"https://ror.org/0170z8493","country_code":"CN","type":"education","lineage":["https://openalex.org/I88830068"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zichen Ma","raw_affiliation_strings":["Shaanxi Normal University,School of Artificial Intelligence and Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Normal University,School of Artificial Intelligence and Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I88830068"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102909930"],"corresponding_institution_ids":["https://openalex.org/I88830068"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.95267585,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1158","last_page":"1161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5238999724388123,"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":0.5238999724388123,"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":0.12389999628067017,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.08209999650716782,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6424999833106995},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5911999940872192},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5683000087738037},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5562999844551086},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5101000070571899},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41690000891685486},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4104999899864197},{"id":"https://openalex.org/keywords/argument","display_name":"Argument (complex analysis)","score":0.3837999999523163},{"id":"https://openalex.org/keywords/model-checking","display_name":"Model checking","score":0.3837999999523163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8266000151634216},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6424999833106995},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5911999940872192},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5683000087738037},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5562999844551086},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5101000070571899},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46160000562667847},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4361000061035156},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4343000054359436},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4007999897003174},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C49895821","wikidata":"https://www.wikidata.org/wiki/Q5227368","display_name":"Data verification","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C202973057","wikidata":"https://www.wikidata.org/wiki/Q7380130","display_name":"Runtime verification","level":3,"score":0.3407000005245209},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C48002344","wikidata":"https://www.wikidata.org/wiki/Q2919644","display_name":"Verification and validation","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.3027999997138977},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.29260000586509705},{"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/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C62460635","wikidata":"https://www.wikidata.org/wiki/Q5508853","display_name":"Functional verification","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C33054407","wikidata":"https://www.wikidata.org/wiki/Q6504747","display_name":"Software verification","level":5,"score":0.25440001487731934},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cnml68938.2026.11453286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11453286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W3034184697","https://openalex.org/W4390873312","https://openalex.org/W4402670285","https://openalex.org/W4405625226","https://openalex.org/W4415708963","https://openalex.org/W7133193597","https://openalex.org/W7133236450"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"excel":[5],"at":[6],"generating":[7],"structured":[8,52],"outputs":[9],"but":[10],"suffer":[11],"from":[12],"hallucination.":[13],"Recent":[14],"work":[15],"shows":[16],"that":[17,96],"LLMs":[18],"cannot":[19,34],"reliably":[20],"self-correct;":[21],"external":[22],"verification":[23,28,67,131],"is":[24],"essential.":[25],"However,":[26],"existing":[27],"methods":[29],"target":[30],"text-only":[31],"scenarios":[32],"and":[33,44,77,91,106,120,137],"assess":[35],"cross-modal":[36,66],"consistency.":[37],"We":[38,58],"introduce":[39],"Cross-modal":[40],"Consistency":[41],"Verification":[42],"(CCV)":[43],"propose":[45],"EVFP":[46],"(Events":[47],"Verifier":[48],"Feedback":[49],"Protocol),":[50],"a":[51,97],"framework":[53],"enabling":[54],"fine-grained":[55],"error":[56],"localization.":[57],"construct":[59],"NAIVE,":[60],"an":[61],"open-source":[62],"weakly-aligned":[63],"dataset":[64],"for":[65,111],"with":[68,109],"approximately":[69],"3,300":[70],"annotated":[71],"samples":[72],"across":[73],"62":[74],"event":[75,115],"types,":[76],"design":[78],"training":[79],"strategies":[80],"to":[81],"fine-tune":[82],"lightweight":[83],"multimodal":[84,133],"models":[85],"as":[86],"verifiers.":[87],"Through":[88],"both":[89],"offline":[90,104],"online":[92],"evaluations,":[93],"we":[94],"demonstrate":[95],"4B":[98],"verifier":[99],"achieves":[100],"91%":[101],"accuracy":[102],"in":[103,132],"validation,":[105],"when":[107],"integrated":[108],"GPT-4o":[110],"iterative":[112,130],"refinement,":[113],"improves":[114],"detection":[116],"recall":[117,123],"by":[118,124],"10.3%":[119],"argument":[121],"extraction":[122],"12.5%,":[125],"validating":[126],"the":[127],"feasibility":[128],"of":[129],"scenarios.":[134],"Code,":[135],"data,":[136],"model":[138],"weights":[139],"are":[140],"publicly":[141],"available.":[142]},"counts_by_year":[],"updated_date":"2026-04-02T13:53:19.096889","created_date":"2026-04-02T00:00:00"}