{"id":"https://openalex.org/W4416017969","doi":"https://doi.org/10.1145/3746252.3760864","title":"Can Large Vision-Language Models Understand Multimodal Sarcasm?","display_name":"Can Large Vision-Language Models Understand Multimodal Sarcasm?","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416017969","doi":"https://doi.org/10.1145/3746252.3760864"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3760864","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3760864","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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746252.3760864","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079329431","display_name":"Xinyu Wang","orcid":"https://orcid.org/0009-0003-5492-8015"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinyu Wang","raw_affiliation_strings":["The University of Texas at Dallas, Richardson, USA"],"raw_orcid":"https://orcid.org/0009-0003-5492-8015","affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas, Richardson, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yue Zhang","orcid":"https://orcid.org/0009-0007-1441-3163"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["The University of Texas at Dallas, Richardson, USA"],"raw_orcid":"https://orcid.org/0009-0007-1441-3163","affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas, Richardson, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051341911","display_name":"Liqiang Jing","orcid":"https://orcid.org/0000-0001-9827-5835"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liqiang Jing","raw_affiliation_strings":["The University of Texas at Dallas, Richardson, USA"],"raw_orcid":"https://orcid.org/0000-0001-9827-5835","affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas, Richardson, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5340","last_page":"5345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.8640000224113464,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.8640000224113464,"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":0.03840000182390213,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.016200000420212746,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sarcasm","display_name":"Sarcasm","score":0.9855999946594238},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5774999856948853},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5515999794006348},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.490200012922287},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3508000075817108},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.303600013256073}],"concepts":[{"id":"https://openalex.org/C2776207355","wikidata":"https://www.wikidata.org/wiki/Q191035","display_name":"Sarcasm","level":3,"score":0.9855999946594238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6456000208854675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5842999815940857},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5774999856948853},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5515999794006348},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.490200012922287},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4417000114917755},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3508000075817108},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2913999855518341},{"id":"https://openalex.org/C2780882242","wikidata":"https://www.wikidata.org/wiki/Q14235582","display_name":"Literal (mathematical logic)","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C46182478","wikidata":"https://www.wikidata.org/wiki/Q7363315","display_name":"Literal and figurative language","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.271699994802475},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C50335755","wikidata":"https://www.wikidata.org/wiki/Q483247","display_name":"Phenomenon","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3760864","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3760864","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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746252.3760864","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3760864","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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2513138008","https://openalex.org/W2951937667","https://openalex.org/W2964126051","https://openalex.org/W3139831923","https://openalex.org/W4284708663","https://openalex.org/W4288055726","https://openalex.org/W4315650895","https://openalex.org/W4367280365","https://openalex.org/W4379034853","https://openalex.org/W4379792729","https://openalex.org/W4384207668","https://openalex.org/W4384642697","https://openalex.org/W4387968274","https://openalex.org/W4391631738","https://openalex.org/W4409363193","https://openalex.org/W4414975281","https://openalex.org/W4416009590"],"related_works":[],"abstract_inverted_index":{"Sarcasm":[0,51,69,73],"is":[1,139],"a":[2,8,88,99],"complex":[3],"linguistic":[4],"phenomenon":[5],"that":[6,102],"involves":[7],"disparity":[9],"between":[10],"literal":[11],"and":[12,21,71,87,107,118],"intended":[13],"meanings,":[14],"making":[15],"it":[16],"challenging":[17],"for":[18],"sentiment":[19],"analysis":[20],"other":[22],"emotion-sensitive":[23],"tasks.":[24],"While":[25],"traditional":[26],"sarcasm":[27,120],"detection":[28],"methods":[29],"primarily":[30],"focus":[31],"on":[32,67,127],"text,":[33],"recent":[34],"approaches":[35],"have":[36],"incorporated":[37],"multimodal":[38,122],"information.":[39],"However,":[40],"the":[41,113,131],"application":[42],"of":[43,90,133],"Large":[44],"Visual":[45],"Language":[46],"Models":[47],"(LVLMs)":[48],"in":[49,62,121],"Multimodal":[50,68,72],"Analysis":[52],"(MSA)":[53],"remains":[54],"underexplored.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59,78,97],"evaluate":[60],"LVLMs":[61],"MSA":[63],"tasks,":[64],"specifically":[65],"focusing":[66],"Detection":[70],"Explanation.":[74],"Through":[75],"comprehensive":[76],"experiments,":[77],"identify":[79],"key":[80],"limitations,":[81],"such":[82],"as":[83],"insufficient":[84],"visual":[85],"understanding":[86],"lack":[89],"conceptual":[91,109],"knowledge.":[92],"To":[93],"address":[94],"these":[95],"issues,":[96],"propose":[98],"training-free":[100],"framework":[101],"integrates":[103],"in-depth":[104],"object":[105],"extraction":[106],"external":[108],"knowledge":[110],"to":[111,116],"improve":[112],"model's":[114],"ability":[115],"interpret":[117],"explain":[119],"contexts.":[123],"The":[124,137],"experimental":[125],"results":[126],"multiple":[128],"models":[129],"show":[130],"effectiveness":[132],"our":[134],"proposed":[135],"framework.":[136],"code":[138],"available":[140],"at":[141],"https://github.com/cp-cp/LVLM-MSA.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}