{"id":"https://openalex.org/W7155391220","doi":"https://doi.org/10.1016/j.inffus.2026.104405","title":"Decoding the multimodal maze: A systematic review on the adoption of explainability in multimodal attention-based models","display_name":"Decoding the multimodal maze: A systematic review on the adoption of explainability in multimodal attention-based models","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W7155391220","doi":"https://doi.org/10.1016/j.inffus.2026.104405"},"language":"en","primary_location":{"id":"doi:10.1016/j.inffus.2026.104405","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.inffus.2026.104405","pdf_url":null,"source":{"id":"https://openalex.org/S7560371","display_name":"Information Fusion","issn_l":"1566-2535","issn":["1566-2535","1872-6305"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Fusion","raw_type":"journal-article"},"type":"review","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.inffus.2026.104405","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004857902","display_name":"Md. Raisul Kibria","orcid":"https://orcid.org/0000-0002-3855-9163"},"institutions":[{"id":"https://openalex.org/I130217899","display_name":"\u00c5bo Akademi University","ror":"https://ror.org/029pk6x14","country_code":"FI","type":"education","lineage":["https://openalex.org/I130217899"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Md Raisul Kibria","raw_affiliation_strings":["Faculty of Science and Engineering, Information Technology, \u00c5bo Akademi University, Turku, 20500, Finland"],"raw_orcid":"https://orcid.org/0000-0002-3855-9163","affiliations":[{"raw_affiliation_string":"Faculty of Science and Engineering, Information Technology, \u00c5bo Akademi University, Turku, 20500, Finland","institution_ids":["https://openalex.org/I130217899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048269070","display_name":"S\u00e9bastien Lafond","orcid":"https://orcid.org/0000-0002-5286-5343"},"institutions":[{"id":"https://openalex.org/I130217899","display_name":"\u00c5bo Akademi University","ror":"https://ror.org/029pk6x14","country_code":"FI","type":"education","lineage":["https://openalex.org/I130217899"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"S\u00e9bastien Lafond","raw_affiliation_strings":["Faculty of Science and Engineering, Information Technology, \u00c5bo Akademi University, Turku, 20500, Finland"],"raw_orcid":"https://orcid.org/0000-0002-5286-5343","affiliations":[{"raw_affiliation_string":"Faculty of Science and Engineering, Information Technology, \u00c5bo Akademi University, Turku, 20500, Finland","institution_ids":["https://openalex.org/I130217899"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034607406","display_name":"Janan Arslan","orcid":"https://orcid.org/0000-0003-2683-3775"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210152724","display_name":"Institut du Cerveau","ror":"https://ror.org/050gn5214","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210096427","https://openalex.org/I4210152724"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Janan Arslan","raw_affiliation_strings":["Sorbonne Universit\u00e9, Institut du Cerveau \u2013 Paris Brain Institute, Paris, F-75013, France"],"raw_orcid":"https://orcid.org/0000-0003-2683-3775","affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9, Institut du Cerveau \u2013 Paris Brain Institute, Paris, F-75013, France","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4210152724"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004857902"],"corresponding_institution_ids":["https://openalex.org/I130217899"],"apc_list":{"value":4740,"currency":"USD","value_usd":4740},"apc_paid":{"value":4740,"currency":"USD","value_usd":4740},"fwci":3.584,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92512909,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"135","issue":null,"first_page":"104405","last_page":"104405"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.7376000285148621,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.7376000285148621,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.03590000048279762,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive 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/T12574","display_name":"Clinical Reasoning and Diagnostic Skills","score":0.014700000174343586,"subfield":{"id":"https://openalex.org/subfields/2714","display_name":"Family Practice"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7610999941825867},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.4523000121116638},{"id":"https://openalex.org/keywords/multimodal-therapy","display_name":"Multimodal therapy","score":0.3206000030040741},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.30399999022483826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7872999906539917},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7610999941825867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4875999987125397},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.4523000121116638},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4284999966621399},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3605000078678131},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3596000075340271},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2644999921321869},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26190000772476196},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1016/j.inffus.2026.104405","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.inffus.2026.104405","pdf_url":null,"source":{"id":"https://openalex.org/S7560371","display_name":"Information Fusion","issn_l":"1566-2535","issn":["1566-2535","1872-6305"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Fusion","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/a2c96f5b-7a8a-4dec-9be9-c6a034e1688e","is_oa":true,"landing_page_url":"https://research.abo.fi/en/publications/a2c96f5b-7a8a-4dec-9be9-c6a034e1688e","pdf_url":null,"source":{"id":"https://openalex.org/S4406923060","display_name":"\u00c5bo Akademi University Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kibria, M R, Lafond, S & Arslan, J 2026, 'Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models', Information Fusion, vol. 135, 104405. https://doi.org/10.1016/j.inffus.2026.104405","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:arXiv.org:2508.04427","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2508.04427","pdf_url":"https://arxiv.org/pdf/2508.04427","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05622345v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05622345","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information Fusion, 2026, pp.104405. ⟨10.1016/j.inffus.2026.104405⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1016/j.inffus.2026.104405","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.inffus.2026.104405","pdf_url":null,"source":{"id":"https://openalex.org/S7560371","display_name":"Information Fusion","issn_l":"1566-2535","issn":["1566-2535","1872-6305"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Fusion","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W2006056627","https://openalex.org/W2023283565","https://openalex.org/W2025653905","https://openalex.org/W2122896223","https://openalex.org/W2150884987","https://openalex.org/W2156098321","https://openalex.org/W2240067561","https://openalex.org/W2277195237","https://openalex.org/W2396881363","https://openalex.org/W2962772482","https://openalex.org/W2964303497","https://openalex.org/W2972324944","https://openalex.org/W2977762603","https://openalex.org/W2981731882","https://openalex.org/W3035422918","https://openalex.org/W3089168780","https://openalex.org/W3089606255","https://openalex.org/W3092695273","https://openalex.org/W3095556657","https://openalex.org/W3101981467","https://openalex.org/W3111057178","https://openalex.org/W3127852407","https://openalex.org/W3134095442","https://openalex.org/W3136907493","https://openalex.org/W3140854437","https://openalex.org/W3161810785","https://openalex.org/W3164846705","https://openalex.org/W3184110467","https://openalex.org/W3187293469","https://openalex.org/W3189411510","https://openalex.org/W3197347140","https://openalex.org/W3200182126","https://openalex.org/W3200411758","https://openalex.org/W3202283490","https://openalex.org/W3205069776","https://openalex.org/W4200350226","https://openalex.org/W4220904955","https://openalex.org/W4224312275","https://openalex.org/W4225844297","https://openalex.org/W4285215850","https://openalex.org/W4289812580","https://openalex.org/W4293083967","https://openalex.org/W4295025118","https://openalex.org/W4296105182","https://openalex.org/W4296467532","https://openalex.org/W4307212054","https://openalex.org/W4307358455","https://openalex.org/W4317384333","https://openalex.org/W4321786089","https://openalex.org/W4322775759","https://openalex.org/W4366490383","https://openalex.org/W4366979886","https://openalex.org/W4376226279","https://openalex.org/W4376274622","https://openalex.org/W4380884710","https://openalex.org/W4381046871","https://openalex.org/W4381108589","https://openalex.org/W4383427955","https://openalex.org/W4385574263","https://openalex.org/W4386755099","https://openalex.org/W4387204747","https://openalex.org/W4387348867","https://openalex.org/W4388693912","https://openalex.org/W4388830671","https://openalex.org/W4389124876","https://openalex.org/W4389519587","https://openalex.org/W4389895915","https://openalex.org/W4390049924","https://openalex.org/W4391836235","https://openalex.org/W4393950444","https://openalex.org/W4399387213","https://openalex.org/W4400645478","https://openalex.org/W4400810536","https://openalex.org/W4401042762","https://openalex.org/W4402809417","https://openalex.org/W4403390366","https://openalex.org/W4403501023","https://openalex.org/W4404356490","https://openalex.org/W4404783092","https://openalex.org/W4404783281","https://openalex.org/W4404958925","https://openalex.org/W4408538044","https://openalex.org/W4408858386","https://openalex.org/W4409387871","https://openalex.org/W7081935942","https://openalex.org/W7133196460"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"learning":[1],"has":[2,37],"witnessed":[3],"remarkable":[4],"advancements":[5],"in":[6,128,155,222,233],"recent":[7,193],"years,":[8],"particularly":[9],"with":[10,112,242],"the":[11,30,47,70,77,84,116,130,142,182],"integration":[12],"of":[13,24,42,51,72,80,133,209],"attention-based":[14,113],"models,":[15,111],"leading":[16],"to":[17,27,229],"significant":[18],"performance":[19],"gains":[20],"across":[21,86,145],"a":[22,39,137,188,206],"variety":[23],"tasks.":[25],"Parallel":[26],"this":[28],"progress,":[29],"demand":[31],"for":[32,120,153,166],"explainable":[33],"artificial":[34],"intelligence":[35],"(XAI)":[36],"spurred":[38],"growing":[40],"body":[41],"research":[43,59,232],"aimed":[44,211],"at":[45,212,244],"interpreting":[46],"complex":[48],"decision-making":[49],"processes":[50],"these":[52,123,174,202],"models.":[53,74],"This":[54],"systematic":[55],"literature":[56,85],"review":[57],"analyzes":[58],"published":[60],"between":[61,135],"January":[62],"2020":[63],"and":[64,96,109,164,169,194,216,219,237],"early":[65],"2024":[66],"that":[67,102,150,191],"focuses":[68],"on":[69,107,201],"explainability":[71,243],"multimodal":[73,156,198,223,239],"Framed":[75],"within":[76],"broader":[78],"goals":[79],"XAI,":[81],"we":[82,148,176,204],"examine":[83],"multiple":[87],"dimensions,":[88],"including":[89],"model":[90],"architecture,":[91],"modalities":[92],"involved,":[93],"explanation":[94],"algorithms":[95],"evaluation":[97,151,218],"methodologies.":[98],"Our":[99,226],"analysis":[100,190],"reveals":[101],"most":[103,117],"studies":[104],"are":[105,158],"concentrated":[106],"vision-language":[108],"language-only":[110],"techniques":[114],"being":[115],"commonly":[118],"employed":[119],"explanation.":[121],"However,":[122],"methods":[124,152],"often":[125],"fall":[126],"short":[127],"capturing":[129],"full":[131],"spectrum":[132],"interactions":[134],"modalities,":[136],"challenge":[138],"further":[139],"compounded":[140],"by":[141],"architectural":[143],"heterogeneity":[144],"domains.":[146],"Importantly,":[147],"find":[149],"XAI":[154,224],"settings":[157],"largely":[159],"non-systematic,":[160],"lacking":[161],"consistency,":[162],"robustness,":[163],"consideration":[165],"modality-specific":[167],"cognitive":[168],"contextual":[170],"factors.":[171],"To":[172],"address":[173],"gaps,":[175],"not":[177],"only":[178],"synthesize":[179],"findings":[180],"from":[181],"surveyed":[183],"works":[184],"but":[185],"also":[186],"incorporate":[187],"complementary":[189],"integrates":[192],"emerging":[195],"advances":[196],"driving":[197],"explainability.":[199],"Based":[200],"insights,":[203],"provide":[205],"comprehensive":[207],"set":[208],"recommendations":[210],"promoting":[213],"rigorous,":[214],"transparent,":[215],"standardized":[217],"reporting":[220],"practices":[221],"research.":[225],"goal":[227],"is":[228],"support":[230],"future":[231],"more":[234],"interpretable,":[235],"accountable,":[236],"responsible":[238],"AI":[240],"systems,":[241],"their":[245],"core.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2026-04-24T00:00:00"}