{"id":"https://openalex.org/W4406273444","doi":"https://doi.org/10.48550/arxiv.2501.05444","title":"Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark","display_name":"Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark","publication_year":2025,"publication_date":"2025-01-09","ids":{"openalex":"https://openalex.org/W4406273444","doi":"https://doi.org/10.48550/arxiv.2501.05444"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2501.05444","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.05444","pdf_url":"https://arxiv.org/pdf/2501.05444","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.05444","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103235198","display_name":"Yi Hao","orcid":"https://orcid.org/0000-0002-4198-6182"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hao, Yunzhuo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015044456","display_name":"Jiawei Gu","orcid":"https://orcid.org/0000-0001-8170-4998"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Jiawei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021497224","display_name":"Huichen Will Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Huichen Will","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100657555","display_name":"Linjie Li","orcid":"https://orcid.org/0000-0003-0867-8863"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Linjie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050209478","display_name":"Zhengyuan Yang","orcid":"https://orcid.org/0000-0002-5808-0889"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zhengyuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436501","display_name":"Lijuan Wang","orcid":"https://orcid.org/0000-0002-2517-2728"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Lijuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100622632","display_name":"Cheng Yu","orcid":"https://orcid.org/0000-0003-4816-1586"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Yu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103235198"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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/T12031","display_name":"Speech and dialogue systems","score":0.9707000255584717,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9531999826431274,"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/multimodality","display_name":"Multimodality","score":0.9740886688232422},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7833519577980042},{"id":"https://openalex.org/keywords/multimodal-therapy","display_name":"Multimodal therapy","score":0.647449791431427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5295910239219666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4178047180175781},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.35282349586486816},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.28540271520614624},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.11068183183670044},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.08138087391853333},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.06543740630149841},{"id":"https://openalex.org/keywords/psychotherapist","display_name":"Psychotherapist","score":0.05886274576187134}],"concepts":[{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.9740886688232422},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7833519577980042},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.647449791431427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5295910239219666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4178047180175781},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.35282349586486816},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.28540271520614624},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11068183183670044},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.08138087391853333},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.06543740630149841},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.05886274576187134}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2501.05444","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.05444","pdf_url":"https://arxiv.org/pdf/2501.05444","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"doi:10.48550/arxiv.2501.05444","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.05444","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.05444","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.05444","pdf_url":"https://arxiv.org/pdf/2501.05444","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4205899436","https://openalex.org/W2462138927","https://openalex.org/W3111427900","https://openalex.org/W4302009627","https://openalex.org/W4212781403","https://openalex.org/W4388989680","https://openalex.org/W4380355808","https://openalex.org/W2558617677","https://openalex.org/W2342456189","https://openalex.org/W2972445698"],"abstract_inverted_index":{"The":[0],"ability":[1,20],"to":[2,27,47,140],"organically":[3],"reason":[4],"over":[5],"and":[6,10,52,71,112,123,137,146],"with":[7,117],"both":[8],"text":[9],"images":[11],"is":[12],"a":[13,61],"pillar":[14],"of":[15,21,100],"human":[16,145],"intelligence,":[17],"yet":[18],"the":[19,131,142],"Multimodal":[22],"Large":[23],"Language":[24],"Models":[25],"(MLLMs)":[26],"perform":[28],"such":[29],"multimodal":[30,65,111,135],"reasoning":[31,39,66,78,84,96,114,148],"remains":[32],"under-explored.":[33],"Existing":[34],"benchmarks":[35],"often":[36],"emphasize":[37],"text-dominant":[38],"or":[40],"rely":[41],"on":[42,103],"shallow":[43],"visual":[44,51],"cues,":[45],"failing":[46],"adequately":[48],"assess":[49],"integrated":[50],"textual":[53],"reasoning.":[54],"We":[55],"introduce":[56],"EMMA":[57,73,104],"(Enhanced":[58],"MultiModal":[59],"reAsoning),":[60],"benchmark":[62],"targeting":[63],"organic":[64],"across":[67],"mathematics,":[68],"physics,":[69],"chemistry,":[70],"coding.":[72],"tasks":[74],"demand":[75],"advanced":[76,118],"cross-modal":[77],"that":[79],"cannot":[80],"be":[81],"addressed":[82],"by":[83],"independently":[85],"in":[86,108,149],"each":[87],"modality,":[88],"offering":[89],"an":[90],"enhanced":[91],"test":[92],"suite":[93],"for":[94,133],"MLLMs'":[95],"capabilities.":[97],"Our":[98],"evaluation":[99],"state-of-the-art":[101],"MLLMs":[102],"reveals":[105],"significant":[106],"limitations":[107],"handling":[109],"complex":[110],"multi-step":[113],"tasks,":[115],"even":[116],"techniques":[119],"like":[120],"Chain-of-Thought":[121],"prompting":[122],"test-time":[124],"compute":[125],"scaling":[126],"underperforming.":[127],"These":[128],"findings":[129],"underscore":[130],"need":[132],"improved":[134],"architectures":[136],"training":[138],"paradigms":[139],"close":[141],"gap":[143],"between":[144],"model":[147],"multimodality.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}