{"id":"https://openalex.org/W7135193280","doi":"https://doi.org/10.48550/arxiv.2603.11689","title":"Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks","display_name":"Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135193280","doi":"https://doi.org/10.48550/arxiv.2603.11689"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.11689","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11689","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2603.11689","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037514890","display_name":"Mei Chee Leong","orcid":"https://orcid.org/0000-0001-8123-8982"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leong, Mei Chee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129080175","display_name":"Ying Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Ying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026930610","display_name":"Hui Li Tan","orcid":"https://orcid.org/0000-0002-3012-9222"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Hui Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128985714","display_name":"Liyuan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Liyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129008394","display_name":"Nancy Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Nancy","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9287999868392944,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9287999868392944,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.01080000028014183,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.007199999876320362,"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.609000027179718},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5896000266075134},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.46480000019073486},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4503999948501587},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.41909998655319214},{"id":"https://openalex.org/keywords/logical-data-model","display_name":"Logical data model","score":0.41609999537467957},{"id":"https://openalex.org/keywords/non-monotonic-logic","display_name":"Non-monotonic logic","score":0.3935000002384186},{"id":"https://openalex.org/keywords/statistical-relational-learning","display_name":"Statistical relational learning","score":0.37630000710487366},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.35420000553131104},{"id":"https://openalex.org/keywords/probabilistic-logic-network","display_name":"Probabilistic logic network","score":0.351500004529953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7203999757766724},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.609000027179718},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5896000266075134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4672999978065491},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.46480000019073486},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4503999948501587},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.41909998655319214},{"id":"https://openalex.org/C203702819","wikidata":"https://www.wikidata.org/wiki/Q17146953","display_name":"Logical data model","level":3,"score":0.41609999537467957},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.382099986076355},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.37630000710487366},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C18998212","wikidata":"https://www.wikidata.org/wiki/Q7246856","display_name":"Probabilistic logic network","level":5,"score":0.351500004529953},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C102993220","wikidata":"https://www.wikidata.org/wiki/Q387196","display_name":"Description logic","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C21847791","wikidata":"https://www.wikidata.org/wiki/Q191081","display_name":"Logical conjunction","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C13606891","wikidata":"https://www.wikidata.org/wiki/Q2623243","display_name":"Conceptual model","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C134752490","wikidata":"https://www.wikidata.org/wiki/Q374182","display_name":"Logical consequence","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28859999775886536},{"id":"https://openalex.org/C74992188","wikidata":"https://www.wikidata.org/wiki/Q239179","display_name":"Non-classical logic","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C160236029","wikidata":"https://www.wikidata.org/wiki/Q842421","display_name":"Default logic","level":5,"score":0.26159998774528503},{"id":"https://openalex.org/C3746660","wikidata":"https://www.wikidata.org/wiki/Q1068763","display_name":"Rule of inference","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C2775940519","wikidata":"https://www.wikidata.org/wiki/Q17067742","display_name":"Logic model","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C20693621","wikidata":"https://www.wikidata.org/wiki/Q6667502","display_name":"Logical framework","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.11689","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11689","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.11689","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11689","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Frontier":[0],"Multimodal":[1],"Large":[2],"Language":[3],"Models":[4],"(MLLMs)":[5],"exhibit":[6],"remarkable":[7],"capabilities":[8],"in":[9,25,50,136],"Visual-Language":[10],"Comprehension":[11],"(VLC)":[12],"tasks.":[13],"However,":[14],"they":[15],"are":[16],"often":[17],"deployed":[18],"as":[19,78],"zero-shot":[20,137],"solution":[21],"to":[22,41,57,146],"new":[23,42],"tasks":[24,138],"a":[26,93,95],"black-box":[27,54],"manner.":[28],"Validating":[29],"and":[30,66,97,106,123,159,183,189,196],"understanding":[31],"the":[32,53,110,178],"behavior":[33],"of":[34,180],"these":[35],"models":[36],"become":[37],"important":[38],"for":[39,62,103,120,152,185],"application":[40],"task.":[43],"We":[44],"propose":[45],"an":[46,79],"Explicit":[47,85],"Logic":[48,81,86],"Channel,":[49,87],"parallel":[51],"with":[52,100,142,165,193],"model":[55,63,124,186],"channel,":[56],"perform":[58],"explicit":[59,111,143],"logical":[60,90,98],"reasoning":[61,99,108],"validation,":[64,187],"selection":[65,188],"enhancement.":[67],"The":[68,83],"frontier":[69,172],"MLLM,":[70],"encapsulating":[71],"latent":[72],"vision-language":[73],"knowledge,":[74],"can":[75],"be":[76],"considered":[77],"Implicit":[80],"Channel.":[82],"proposed":[84,119,181],"mimicking":[88],"human":[89],"reasoning,":[91],"incorporates":[92],"LLM,":[94],"VFM,":[96],"probabilistic":[101],"inference":[102],"factual,":[104],"counterfactual,":[105],"relational":[107],"over":[109,139],"visual":[112,144],"evidence.":[113],"A":[114],"Consistency":[115],"Rate":[116],"(CR)":[117],"is":[118],"cross-channel":[121,131],"validation":[122],"selection,":[125],"even":[126],"without":[127],"ground-truth":[128],"annotations.":[129],"Additionally,":[130],"integration":[132],"further":[133],"improves":[134],"performance":[135],"MLLMs,":[140],"grounded":[141],"evidence":[145],"enhance":[147],"trustworthiness.":[148,197],"Comprehensive":[149],"experiments":[150],"conducted":[151],"two":[153],"representative":[154],"VLC":[155],"tasks,":[156],"i.e.,":[157],"MC-VQA":[158],"HC-REC,":[160],"on":[161,191],"three":[162],"challenging":[163],"benchmarks,":[164],"11":[166],"recent":[167],"open-source":[168],"MLLMs":[169,192],"from":[170],"4":[171],"families.":[173],"Our":[174],"systematic":[175],"evaluations":[176],"demonstrate":[177],"effectiveness":[179],"ELC":[182],"CR":[184],"improvement":[190],"enhanced":[194],"explainability":[195]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-14T00:00:00"}