{"id":"https://openalex.org/W4415537788","doi":"https://doi.org/10.1145/3746027.3755711","title":"ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs: ShieldVLM","display_name":"ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs: ShieldVLM","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537788","doi":"https://doi.org/10.1145/3746027.3755711"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755711","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755711","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/10.1145/3746027.3755711","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028351629","display_name":"Shiyao Cui","orcid":"https://orcid.org/0009-0003-2333-1064"},"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":"Shiyao Cui","raw_affiliation_strings":["The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-2333-1064","affiliations":[{"raw_affiliation_string":"The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111837778","display_name":"Qinglin Zhang","orcid":"https://orcid.org/0009-0009-5270-3801"},"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":"QingLin Zhang","raw_affiliation_strings":["The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-5270-3801","affiliations":[{"raw_affiliation_string":"The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109461795","display_name":"Xuan Ouyang","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xuan Ouyang","raw_affiliation_strings":["The Conversational AI (CoAI) group, DCST, University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0009-0005-4115-7340","affiliations":[{"raw_affiliation_string":"The Conversational AI (CoAI) group, DCST, University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010074373","display_name":"Renmiao Chen","orcid":"https://orcid.org/0009-0001-1213-0916"},"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":"Renmiao Chen","raw_affiliation_strings":["The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-1213-0916","affiliations":[{"raw_affiliation_string":"The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102245113","display_name":"Zhexin Zhang","orcid":null},"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":"Zhexin Zhang","raw_affiliation_strings":["The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-9601-3991","affiliations":[{"raw_affiliation_string":"The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108314704","display_name":"Yida Lu","orcid":null},"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":"Yida Lu","raw_affiliation_strings":["The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-4492-9047","affiliations":[{"raw_affiliation_string":"The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085094109","display_name":"Hongning Wang","orcid":"https://orcid.org/0000-0002-6524-9195"},"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":"Hongning Wang","raw_affiliation_strings":["The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6524-9195","affiliations":[{"raw_affiliation_string":"The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019692903","display_name":"Han Qiu","orcid":"https://orcid.org/0000-0003-2678-8070"},"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":"Han Qiu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2678-8070","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044042138","display_name":"Minlie Huang","orcid":"https://orcid.org/0000-0001-7111-1849"},"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":"Minlie Huang","raw_affiliation_strings":["The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7111-1849","affiliations":[{"raw_affiliation_string":"The Conversational AI (CoAI) group, DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11677","last_page":"11686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9998000264167786,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9998000264167786,"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":0.9822999835014343,"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/T10028","display_name":"Topic Modeling","score":0.9476000070571899,"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/multimodal-therapy","display_name":"Multimodal therapy","score":0.5138000249862671},{"id":"https://openalex.org/keywords/safeguarding","display_name":"Safeguarding","score":0.438400000333786},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.3824999928474426},{"id":"https://openalex.org/keywords/hazard","display_name":"Hazard","score":0.3492000102996826},{"id":"https://openalex.org/keywords/accident","display_name":"Accident (philosophy)","score":0.271699994802475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6029000282287598},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.5138000249862671},{"id":"https://openalex.org/C2776743756","wikidata":"https://www.wikidata.org/wiki/Q5097921","display_name":"Safeguarding","level":2,"score":0.438400000333786},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3686000108718872},{"id":"https://openalex.org/C49261128","wikidata":"https://www.wikidata.org/wiki/Q1132455","display_name":"Hazard","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C2780289543","wikidata":"https://www.wikidata.org/wiki/Q424630","display_name":"Accident (philosophy)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2443999946117401},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.24300000071525574}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755711","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755711","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:10.1145/3746027.3755711","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755711","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W3009899658","https://openalex.org/W3176580738","https://openalex.org/W4205734215","https://openalex.org/W4290943938","https://openalex.org/W4382318449","https://openalex.org/W4385570945","https://openalex.org/W4385573297","https://openalex.org/W4385977411","https://openalex.org/W4389261241","https://openalex.org/W4389713766","https://openalex.org/W4390601282","https://openalex.org/W4394007075","https://openalex.org/W4394709004","https://openalex.org/W4399836788","https://openalex.org/W4399991227","https://openalex.org/W4401306838","https://openalex.org/W4401306886","https://openalex.org/W4402671302","https://openalex.org/W4403344692","https://openalex.org/W4403853618","https://openalex.org/W4403878024","https://openalex.org/W4404721902","https://openalex.org/W4404792857","https://openalex.org/W4405031664","https://openalex.org/W4405172832","https://openalex.org/W4405355299","https://openalex.org/W4406485177","https://openalex.org/W4407012568","https://openalex.org/W4407764259","https://openalex.org/W4407794264","https://openalex.org/W4414846786"],"related_works":[],"abstract_inverted_index":{"Toxicity":[0],"detection":[1,63,113],"in":[2,36,56,127,145],"multimodal":[3,11,65,69,84,94,115,128],"text-image":[4],"content":[5],"faces":[6],"growing":[7],"challenges,":[8],"especially":[9],"with":[10],"implicit":[12,28,70,85,116,125,148],"toxicity,":[13,71,117],"where":[14],"each":[15],"modality":[16],"appears":[17,30],"benign":[18],"on":[19],"its":[20],"own":[21],"but":[22,39],"conveys":[23],"hazard":[24],"when":[25],"combined.":[26],"Multimodal":[27],"toxicity":[29,62,86,126],"not":[31],"only":[32],"as":[33],"formal":[34],"statements":[35,95],"social":[37],"platforms":[38],"also":[40],"prompts":[41,97,130],"that":[42,139],"can":[43],"lead":[44],"to":[45,160],"toxic":[46],"dialogs":[47,132],"from":[48],"Large":[49],"Vision-Language":[50],"Models":[51],"(LVLMs).":[52],"Despite":[53],"the":[54,68,112],"success":[55],"unimodal":[57],"text":[58],"or":[59],"image":[60],"moderation,":[61],"for":[64,83],"content,":[66],"particularly":[67],"remains":[72],"underexplored.":[73],"To":[74,110],"fill":[75],"this":[76],"gap,":[77],"we":[78,118],"comprehensively":[79],"build":[80,119],"a":[81,121],"taxonomy":[82],"(MMIT)":[87],"and":[88,96,104,131,149,154],"introduce":[89],"an":[90],"MMIT-dataset,":[91],"comprising":[92],"2,100":[93],"across":[98],"7":[99],"risk":[100],"categories":[101],"(31":[102],"sub-categories)":[103],"5":[105],"typical":[106],"cross-modal":[107,135],"correlation":[108],"modes.":[109],"advance":[111],"of":[114],"ShieldVLM,":[120],"model":[122,153],"which":[123],"identifies":[124],"statements,":[129],"via":[133],"deliberative":[134],"reasoning.":[136],"Experiments":[137],"show":[138],"ShieldVLM":[140],"outperforms":[141],"existing":[142],"strong":[143],"baselines":[144],"detecting":[146],"both":[147],"explicit":[150],"toxicity.":[151],"The":[152],"dataset":[155],"will":[156],"be":[157],"publicly":[158],"available":[159],"support":[161],"future":[162],"researches":[163],"(Warning:":[164],"This":[165,172],"paper":[166,173],"contains":[167,174],"potentially":[168,175],"sensitive":[169,176],"contents).":[170],"Warning:":[171],"contents.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}