{"id":"https://openalex.org/W4411237422","doi":"https://doi.org/10.1145/3708319.3733648","title":"Exploring the Potential of Multimodal Large Language Models for Question Answering on Artworks","display_name":"Exploring the Potential of Multimodal Large Language Models for Question Answering on Artworks","publication_year":2025,"publication_date":"2025-06-12","ids":{"openalex":"https://openalex.org/W4411237422","doi":"https://doi.org/10.1145/3708319.3733648"},"language":"en","primary_location":{"id":"doi:10.1145/3708319.3733648","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3708319.3733648","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3708319.3733648","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3708319.3733648","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026091557","display_name":"Alessio Ferrato","orcid":"https://orcid.org/0000-0001-5405-3018"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Alessio Ferrato","raw_affiliation_strings":["Roma Tre University, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0001-5405-3018","affiliations":[{"raw_affiliation_string":"Roma Tre University, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070750659","display_name":"Carla Limongelli","orcid":"https://orcid.org/0000-0002-0323-7738"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Carla Limongelli","raw_affiliation_strings":["Roma Tre University, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0002-0323-7738","affiliations":[{"raw_affiliation_string":"Roma Tre University, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036332666","display_name":"Fabio Gasparetti","orcid":"https://orcid.org/0000-0003-0263-531X"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Gasparetti","raw_affiliation_strings":["Roma Tre University, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0003-0263-531X","affiliations":[{"raw_affiliation_string":"Roma Tre University, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089623580","display_name":"Giuseppe Sansonetti","orcid":"https://orcid.org/0000-0003-4953-1390"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giuseppe Sansonetti","raw_affiliation_strings":["Roma Tre University, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4953-1390","affiliations":[{"raw_affiliation_string":"Roma Tre University, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023673758","display_name":"Alessandro Micarelli","orcid":"https://orcid.org/0000-0001-6508-8021"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Micarelli","raw_affiliation_strings":["Roma Tre University, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0001-6508-8021","affiliations":[{"raw_affiliation_string":"Roma Tre University, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5026091557"],"corresponding_institution_ids":["https://openalex.org/I119003972"],"apc_list":null,"apc_paid":null,"fwci":2.2665,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88389381,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"432","last_page":"436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9832000136375427,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9812999963760376,"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/computer-science","display_name":"Computer science","score":0.7471932172775269},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7354223728179932},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5468149781227112},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44121164083480835},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.39059093594551086},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.0817556083202362}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7471932172775269},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7354223728179932},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5468149781227112},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44121164083480835},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.39059093594551086},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0817556083202362}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3708319.3733648","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3708319.3733648","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3708319.3733648","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma3.it:11590/521177","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.1145/3708319.3733648","pdf_url":null,"source":{"id":"https://openalex.org/S4377196120","display_name":"Iris (Roma Tre University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119003972","host_organization_name":"Roma Tre University","host_organization_lineage":["https://openalex.org/I119003972"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3708319.3733648","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3708319.3733648","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3708319.3733648","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411237422.pdf","grobid_xml":"https://content.openalex.org/works/W4411237422.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W280485258","https://openalex.org/W1513194152","https://openalex.org/W1534643234","https://openalex.org/W1600977779","https://openalex.org/W1876505008","https://openalex.org/W1990080833","https://openalex.org/W2101105183","https://openalex.org/W2950405873","https://openalex.org/W2961452201","https://openalex.org/W2990138404","https://openalex.org/W2992301976","https://openalex.org/W3012716110","https://openalex.org/W3042279863","https://openalex.org/W3098967712","https://openalex.org/W3127724266","https://openalex.org/W3216580327","https://openalex.org/W4284700492","https://openalex.org/W4320736349","https://openalex.org/W4362554621","https://openalex.org/W4386421234","https://openalex.org/W4396844090","https://openalex.org/W4400106310","https://openalex.org/W4402442386","https://openalex.org/W4406899450","https://openalex.org/W4407049645"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,30,43,90],"application":[4],"of":[5,33],"a":[6,116],"Multimodal":[7],"Large":[8],"Language":[9,36],"Model":[10],"to":[11,106,110],"enhance":[12,101],"visitor":[13,118],"experiences":[14],"in":[15],"cultural":[16],"heritage":[17],"settings":[18],"through":[19,60],"Visual":[20],"Question":[21,26],"Answering":[22,27],"(VQA)":[23],"and":[24,37,57],"Contextual":[25],"(CQA).We":[28],"evaluate":[29],"zero-shot":[31],"capabilities":[32],"LLaVA-7b":[34],"(Large":[35],"Vision":[38],"Assistant)":[39],"on":[40,71],"QA":[41],"using":[42,115],"AQUA":[44],"dataset.We":[45],"assess":[46],"how":[47,105],"effectively":[48],"it":[49],"can":[50],"answer":[51],"questions":[52,81],"about":[53],"artwork,":[54],"visual":[55,72],"content,":[56],"contextual":[58,83],"information":[59],"three":[61],"experimental":[62],"approaches.Our":[63],"findings":[64],"reveal":[65],"that":[66],"LLaVA":[67],"demonstrates":[68],"promising":[69],"performance":[70],"questions,":[73],"outperforming":[74],"previous":[75],"baselines":[76],"but":[77],"facing":[78],"challenges":[79],"with":[80],"requiring":[82],"understanding.The":[84],"selective":[85],"knowledge":[86,97],"integration":[87],"approach":[88],"showed":[89],"best":[91],"overall":[92],"performance,":[93],"suggesting":[94],"an":[95],"efficient":[96],"retrieval":[98],"systems":[99],"could":[100],"performance.Moreover,":[102],"we":[103],"show":[104],"exploit":[107],"such":[108],"models":[109],"provide":[111],"correct":[112],"personalized":[113],"answers":[114],"well-established":[117],"model.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}