{"id":"https://openalex.org/W4416060564","doi":"https://doi.org/10.1145/3796722","title":"MLlm-DR: Towards Explainable Depression Recognition with MultiModal Large Language Models","display_name":"MLlm-DR: Towards Explainable Depression Recognition with MultiModal Large Language Models","publication_year":2026,"publication_date":"2026-02-13","ids":{"openalex":"https://openalex.org/W4416060564","doi":"https://doi.org/10.1145/3796722"},"language":"en","primary_location":{"id":"doi:10.1145/3796722","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3796722","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.05591","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wei Zhang","orcid":"https://orcid.org/0009-0009-8079-3349"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0009-8079-3349","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Juan Chen","orcid":"https://orcid.org/0009-0000-8703-7276"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juan Chen","raw_affiliation_strings":["University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-8703-7276","affiliations":[{"raw_affiliation_string":"University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069681054","display_name":"En Zhu","orcid":"https://orcid.org/0000-0003-2305-7555"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"En Zhu","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-2305-7555","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048840363","display_name":"Wenhong Cheng","orcid":"https://orcid.org/0000-0003-4469-9442"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I2802690428","display_name":"Shanghai Mental Health Center","ror":"https://ror.org/05bd2wa15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I2802690428"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhong Cheng","raw_affiliation_strings":["Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4469-9442","affiliations":[{"raw_affiliation_string":"Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I2802690428"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013240205","display_name":"YunPeng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]},{"id":"https://openalex.org/I4210101451","display_name":"Nanjing University of Industry Technology","ror":"https://ror.org/00qf07q44","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210101451"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunpeng Li","raw_affiliation_strings":["Nanjing Industria Tenebris Information Technology Co., Ltd., Nanjing, China","National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0008-4338-4960","affiliations":[{"raw_affiliation_string":"Nanjing Industria Tenebris Information Technology Co., Ltd., Nanjing, China","institution_ids":["https://openalex.org/I4210101451"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuhan Li","orcid":"https://orcid.org/0009-0007-1301-3416"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]},{"id":"https://openalex.org/I4210101451","display_name":"Nanjing University of Industry Technology","ror":"https://ror.org/00qf07q44","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210101451"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhan Li","raw_affiliation_strings":["Nanjing Industria Tenebris Information Technology Co., Ltd., Nanjing, China","National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0007-1301-3416","affiliations":[{"raw_affiliation_string":"Nanjing Industria Tenebris Information Technology Co., Ltd., Nanjing, China","institution_ids":["https://openalex.org/I4210101451"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yanbo J Wang","orcid":"https://orcid.org/0009-0008-0658-930X"},"institutions":[{"id":"https://openalex.org/I47151758","display_name":"National University of Uzbekistan","ror":"https://ror.org/011647w73","country_code":"UZ","type":"education","lineage":["https://openalex.org/I47151758"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Yanbo J Wang","raw_affiliation_strings":["National University of Uzbekistan named after Mirzo Ulugbek, Tashkent, Uzbekistan"],"raw_orcid":"https://orcid.org/0009-0008-0658-930X","affiliations":[{"raw_affiliation_string":"National University of Uzbekistan named after Mirzo Ulugbek, Tashkent, Uzbekistan","institution_ids":["https://openalex.org/I47151758"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":43.5911,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.99603092,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"22","issue":"4","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.743399977684021,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.743399977684021,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/T10667","display_name":"Emotion and Mood Recognition","score":0.12200000137090683,"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/T11519","display_name":"Digital Mental Health Interventions","score":0.05169999971985817,"subfield":{"id":"https://openalex.org/subfields/3202","display_name":"Applied Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/depression","display_name":"Depression (economics)","score":0.7050999999046326},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.6230000257492065},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4810999929904938},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47620001435279846},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.31929999589920044}],"concepts":[{"id":"https://openalex.org/C2776867660","wikidata":"https://www.wikidata.org/wiki/Q1814941","display_name":"Depression (economics)","level":2,"score":0.7050999999046326},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6230000257492065},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4810999929904938},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.478300005197525},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.44130000472068787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43309998512268066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.400299996137619},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3343000113964081},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32350000739097595},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2703999876976013}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3796722","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3796722","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2507.05591","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.05591","pdf_url":"https://arxiv.org/pdf/2507.05591","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"doi:10.48550/arxiv.2507.05591","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.05591","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.05591","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.05591","pdf_url":"https://arxiv.org/pdf/2507.05591","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2127012489","https://openalex.org/W4386813249","https://openalex.org/W3209984917","https://openalex.org/W4415795657","https://openalex.org/W2194775991","https://openalex.org/W4408611773","https://openalex.org/W2191779130","https://openalex.org/W3202866789","https://openalex.org/W3094259155","https://openalex.org/W4318960851","https://openalex.org/W4405045106","https://openalex.org/W4391216244"],"related_works":[],"abstract_inverted_index":{"Clinical":[0],"depression":[1,34,79],"diagnosis":[2],"relies":[3],"heavily":[4],"on":[5,170],"both":[6],"verbal":[7],"and":[8,23,48,124,127,154,159,176,183],"non-verbal":[9],"cues":[10,120],"in":[11,54,137],"patient":[12],"interviews,":[13],"yet":[14],"existing":[15],"automated":[16],"methods":[17],"often":[18,59],"operate":[19],"as":[20],"black-box":[21],"models":[22],"fail":[24],"to":[25,44,86,95],"provide":[26],"trustworthy":[27],"explanations,":[28],"limiting":[29],"their":[30],"clinical":[31],"applicability.":[32],"Moreover,":[33],"datasets":[35],"commonly":[36],"impose":[37],"strict":[38],"privacy":[39],"constraints":[40],"that":[41,116,149,165],"prohibit":[42],"access":[43],"raw":[45],"audio\u2013visual":[46],"data,":[47],"the":[49],"deployment":[50],"of":[51],"large":[52,74],"LLMs":[53,94],"real-world":[55],"medical":[56],"environments":[57],"is":[58,135],"constrained":[60],"by":[61,146],"computational":[62],"cost":[63],"limitations.":[64],"To":[65],"address":[66],"these":[67],"challenges,":[68],"we":[69],"propose":[70],"MLlm-DR,":[71],"a":[72,92,96,111],"multimodal":[73,140],"language":[75],"model":[76],"for":[77],"explainable":[78],"recognition.":[80],"We":[81,108],"first":[82],"employ":[83],"knowledge":[84],"distillation":[85],"transfer":[87],"high-quality":[88],"diagnostic":[89],"rationales":[90],"from":[91,121],"powerful":[93],"smaller,":[97],"deployable":[98],"LLMs,":[99],"thereby":[100],"equipping":[101],"it":[102],"with":[103],"clinically":[104,181],"aligned":[105],"reasoning":[106],"abilities.":[107],"further":[109],"introduce":[110],"lightweight":[112],"query":[113],"module":[114],"(LQ-former)":[115],"extracts":[117],"salient":[118],"depression-related":[119],"pre-extracted":[122],"audio":[123],"visual":[125],"features":[126],"maps":[128],"them":[129],"into":[130],"an":[131],"LLM-compatible":[132],"representation.":[133],"MLlm-DR":[134,166],"trained":[136],"two":[138,171],"stages:":[139],"alignment":[141],"via":[142],"LQ-former":[143],"pretraining,":[144],"followed":[145],"multi-task":[147],"optimization":[148],"jointly":[150],"learns":[151],"rationale":[152],"generation":[153],"score":[155],"regression,":[156],"encouraging":[157],"consistency":[158],"improving":[160],"interpretability.":[161],"Experimental":[162],"results":[163],"show":[164],"achieves":[167],"state-of-the-art":[168],"performance":[169],"interview-based":[172],"benchmark":[173],"datasets,":[174],"CMDC":[175],"E-DAIC-WOZ,":[177],"while":[178],"simultaneously":[179],"generating":[180],"meaningful":[182],"readable":[184],"explanations.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}