{"id":"https://openalex.org/W4416252103","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228995","title":"Role-Playing in Vision-Language Models: A Comprehensive Evaluation of Image Description Performance","display_name":"Role-Playing in Vision-Language Models: A Comprehensive Evaluation of Image Description Performance","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252103","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228995"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5037709945","display_name":"Zhaofeng Niu","orcid":"https://orcid.org/0000-0001-9894-4584"},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaofeng Niu","raw_affiliation_strings":["Qufu Normal University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qufu Normal University,China","institution_ids":["https://openalex.org/I202126657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010644779","display_name":"Xiaoya Chang","orcid":"https://orcid.org/0009-0009-1941-4602"},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoya Chang","raw_affiliation_strings":["Qufu Normal University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qufu Normal University,China","institution_ids":["https://openalex.org/I202126657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412545","display_name":"Bowen Wang","orcid":"https://orcid.org/0000-0002-2911-5595"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Bowen Wang","raw_affiliation_strings":["Osaka University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University,Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022865501","display_name":"Xingfu Cheng","orcid":"https://orcid.org/0009-0008-1937-3727"},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingfu Cheng","raw_affiliation_strings":["Qufu Normal University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qufu Normal University,China","institution_ids":["https://openalex.org/I202126657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013763732","display_name":"Guangshun Li","orcid":"https://orcid.org/0000-0001-6147-0637"},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangshun Li","raw_affiliation_strings":["Qufu Normal University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qufu Normal University,China","institution_ids":["https://openalex.org/I202126657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071266785","display_name":"Liangzhi Li","orcid":"https://orcid.org/0000-0002-8879-5957"},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangzhi Li","raw_affiliation_strings":["Qufu Normal University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qufu Normal University,China","institution_ids":["https://openalex.org/I202126657"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39712785,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.986299991607666,"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":0.986299991607666,"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/T10028","display_name":"Topic Modeling","score":0.0034000000450760126,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0020000000949949026,"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/task","display_name":"Task (project management)","score":0.6898999810218811},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4011000096797943},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.362199991941452},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3456999957561493},{"id":"https://openalex.org/keywords/systematic-review","display_name":"Systematic review","score":0.31040000915527344}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6898999810218811},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6444000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4343999922275543},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.362199991941452},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3481999933719635},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.31040000915527344},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2935999929904938},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27549999952316284},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26339998841285706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2019236394","https://openalex.org/W2619383789","https://openalex.org/W3126813021","https://openalex.org/W4327545654","https://openalex.org/W4385570392","https://openalex.org/W4386071596","https://openalex.org/W4388488609","https://openalex.org/W4389519488","https://openalex.org/W4391094120","https://openalex.org/W4393118106","https://openalex.org/W4400216869","https://openalex.org/W4401834466","https://openalex.org/W4402670135","https://openalex.org/W4402670540","https://openalex.org/W4402671884","https://openalex.org/W4402675481","https://openalex.org/W4404356490","https://openalex.org/W4404781205","https://openalex.org/W4411403346","https://openalex.org/W4411630047","https://openalex.org/W4415797087"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,69,92,95,98,119,141,158],"significant":[2],"advances":[3],"made":[4],"in":[5,21,55,150],"large":[6],"language":[7],"models":[8,12,104],"(LLMs)":[9],"and":[10,81,115,167],"vision-language":[11],"(VLMs),":[13],"research":[14],"on":[15],"role-playing":[16,34,70,148],"(RP)":[17],"within":[18],"VLMs":[19,101,151],"remains":[20],"its":[22],"nascent":[23],"stages,":[24],"with":[25,133],"a":[26,61,144],"conspicuous":[27],"lack":[28],"of":[29,32,72,84,94,100,121,147,160],"systematic":[30,145],"evaluations":[31],"their":[33],"capabilities.":[35],"This":[36,136],"study":[37,137],"aims":[38],"to":[39,49,67],"address":[40],"this":[41],"gap":[42],"by":[43],"exploring":[44],"how":[45],"specific":[46],"prompts":[47],"related":[48],"different":[50],"roles":[51,96,107,123],"influence":[52],"VLM":[53],"performance":[54,99],"image":[56],"description":[57],"tasks.":[58],"We":[59],"propose":[60],"comprehensive":[62],"evaluation":[63],"framework":[64],"specifically":[65],"designed":[66],"assess":[68],"abilities":[71],"VLMs,":[73],"encompassing":[74],"classification":[75],"accuracy,":[76],"semantic":[77],"similarity,":[78],"lexical":[79],"diversity,":[80],"potential":[82],"hazards":[83],"generated":[85],"content.":[86],"Our":[87],"findings":[88],"indicate":[89],"that":[90,110,163],"as":[91],"age":[93],"increases,":[97],"improves":[102],"significantly;":[103],"portraying":[105],"older":[106],"produce":[108],"descriptions":[109],"are":[111],"semantically":[112],"more":[113],"accurate":[114],"contextually":[116],"richer.":[117],"Furthermore,":[118],"introduction":[120],"domain-specific":[122],"markedly":[124],"enhances":[125],"model":[126],"performance,":[127],"particularly":[128],"when":[129],"expert":[130],"knowledge":[131],"aligns":[132],"task":[134],"requirements.":[135],"not":[138],"only":[139],"underscores":[140],"necessity":[142],"for":[143,157],"assessment":[146],"capabilities":[149],"but":[152],"also":[153],"provides":[154],"valuable":[155],"insights":[156],"development":[159],"multimodal":[161],"systems":[162],"exhibit":[164],"contextual":[165],"awareness":[166],"moral":[168],"responsibility":[169],"across":[170],"various":[171],"applications.":[172]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-14T00:00:00"}