{"id":"https://openalex.org/W4406356828","doi":"https://doi.org/10.1109/ictc62082.2024.10827294","title":"What is the True Performance of Large Multimodal Models in Visual Context-Based Mathematical Reasoning? An Analysis of Multiple Datasets and Future Research Directions","display_name":"What is the True Performance of Large Multimodal Models in Visual Context-Based Mathematical Reasoning? An Analysis of Multiple Datasets and Future Research Directions","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4406356828","doi":"https://doi.org/10.1109/ictc62082.2024.10827294"},"language":"en","primary_location":{"id":"doi:10.1109/ictc62082.2024.10827294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc62082.2024.10827294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 15th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"},"type":"article","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/A5100734345","display_name":"Jieun Park","orcid":"https://orcid.org/0000-0003-2972-4849"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jieun Park","raw_affiliation_strings":["Tutorus Labs Inc.,AI Lab,Daejeon,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Tutorus Labs Inc.,AI Lab,Daejeon,Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114034854","display_name":"Sungeun Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sungeun Park","raw_affiliation_strings":["Tutorus Labs Inc.,AI Lab,Daejeon,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Tutorus Labs Inc.,AI Lab,Daejeon,Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072274879","display_name":"Hyung\u2010Bae Jeon","orcid":"https://orcid.org/0000-0001-8650-5154"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyungbae Jeon","raw_affiliation_strings":["Tutorus Labs Inc.,AI Lab,Daejeon,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Tutorus Labs Inc.,AI Lab,Daejeon,Republic of Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007275504","display_name":"Joonho Lim","orcid":"https://orcid.org/0000-0002-4556-1536"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joon-Ho Lim","raw_affiliation_strings":["Tutorus Labs Inc.,AI Lab,Daejeon,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Tutorus Labs Inc.,AI Lab,Daejeon,Republic of Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100734345"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23558841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"854","last_page":"859"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.866100013256073,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.866100013256073,"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/T10731","display_name":"Educational Games and Gamification","score":0.8578000068664551,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10130","display_name":"Mathematics Education and Teaching Techniques","score":0.8194000124931335,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7458333969116211},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6420433521270752},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5697395205497742},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4984424114227295},{"id":"https://openalex.org/keywords/interactive-visual-analysis","display_name":"Interactive visual analysis","score":0.4283354580402374},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.420405775308609},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37197279930114746},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.35548555850982666},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35157930850982666},{"id":"https://openalex.org/keywords/visual-analytics","display_name":"Visual analytics","score":0.295332133769989}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7458333969116211},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6420433521270752},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5697395205497742},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4984424114227295},{"id":"https://openalex.org/C99740376","wikidata":"https://www.wikidata.org/wiki/Q17092520","display_name":"Interactive visual analysis","level":4,"score":0.4283354580402374},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.420405775308609},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37197279930114746},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35548555850982666},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35157930850982666},{"id":"https://openalex.org/C59732488","wikidata":"https://www.wikidata.org/wiki/Q2528440","display_name":"Visual analytics","level":3,"score":0.295332133769989},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc62082.2024.10827294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc62082.2024.10827294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 15th International Conference on Information and Communication Technology Convergence (ICTC)","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":8,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2250564385","https://openalex.org/W2963420691","https://openalex.org/W3176186248","https://openalex.org/W4247348637","https://openalex.org/W4402716477","https://openalex.org/W4403808928","https://openalex.org/W4404781880"],"related_works":["https://openalex.org/W4390204044","https://openalex.org/W3041760129","https://openalex.org/W3175352000","https://openalex.org/W2923661510","https://openalex.org/W2105200106","https://openalex.org/W2571228289","https://openalex.org/W2362367986","https://openalex.org/W2006240110","https://openalex.org/W2771576151","https://openalex.org/W2751110224"],"abstract_inverted_index":{"In":[0],"this":[1,58,83],"paper,":[2],"we":[3],"study":[4],"the":[5,13,75,99,110],"capability":[6],"of":[7,17,77,89,101,112],"visual":[8,23,42,93],"context-based":[9,24,94],"mathematical":[10,25,95],"reasoning":[11,26,96],"within":[12],"rapidly":[14],"evolving":[15],"field":[16],"Large":[18],"Multimodal":[19],"Models":[20],"(LMMs).":[21],"Achieving":[22],"requires":[27],"cognitive":[28],"skills":[29],"similar":[30],"to":[31,56,64,92,108],"those":[32],"used":[33],"in":[34],"human":[35],"reasoning,":[36],"as":[37],"it":[38],"involves":[39],"inter-preting":[40],"diverse":[41],"elements":[43],"and":[44,70,97,115],"converting":[45],"them":[46],"into":[47],"mathe-matical":[48],"representations.":[49],"Previous":[50],"research":[51,118],"has":[52],"explored":[53],"various":[54],"methodologies":[55],"address":[57],"challenge,":[59],"but":[60],"these":[61,104],"approaches":[62],"tend":[63],"work":[65],"only":[66],"under":[67],"specific":[68],"conditions":[69],"are":[71],"often":[72],"constrained":[73],"by":[74],"limitations":[76,111],"available":[78],"datasets.":[79,105],"As":[80],"a":[81,86],"result,":[82],"paper":[84],"offers":[85],"comprehensive":[87],"analysis":[88],"datasets":[90],"related":[91],"evaluates":[98],"effectiveness":[100],"LMMs":[102],"using":[103],"We":[106],"aim":[107],"identify":[109],"existing":[113],"techniques":[114],"suggest":[116],"future":[117],"directions.":[119]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}