{"id":"https://openalex.org/W7126019497","doi":"https://doi.org/10.1109/bibm66473.2025.11356556","title":"Multi-Strategy Collaborative Training of Large Language Models for Depression Text Generation and Detection","display_name":"Multi-Strategy Collaborative Training of Large Language Models for Depression Text Generation and Detection","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126019497","doi":"https://doi.org/10.1109/bibm66473.2025.11356556"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356556","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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/A5124208293","display_name":"Zhengnan Qiao","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhengnan Qiao","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University,Hohhot,China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100430876","display_name":"Xi Zhang","orcid":"https://orcid.org/0000-0003-3415-5345"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianguo Zhang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University,Hohhot,China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5124208293"],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80235479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7638","last_page":"7644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.9549999833106995,"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":0.9549999833106995,"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/T11519","display_name":"Digital Mental Health Interventions","score":0.020999999716877937,"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"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.004100000020116568,"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/robustness","display_name":"Robustness (evolution)","score":0.6805999875068665},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.6686999797821045},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6662999987602234},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6039000153541565},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5354999899864197},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.40230000019073486},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.3643999993801117}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7195000052452087},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6805999875068665},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.6686999797821045},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6662999987602234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6608999967575073},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6039000153541565},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5354999899864197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5045999884605408},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43849998712539673},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3643999993801117},{"id":"https://openalex.org/C1921717","wikidata":"https://www.wikidata.org/wiki/Q1334846","display_name":"Mahalanobis distance","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356556","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7218486070632935,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2953413710","https://openalex.org/W2963261455","https://openalex.org/W2970641574","https://openalex.org/W2972968667","https://openalex.org/W3085890295","https://openalex.org/W4297499142","https://openalex.org/W4402273552","https://openalex.org/W7124131577"],"related_works":[],"abstract_inverted_index":{"Early":[0],"identification":[1],"of":[2,5,23,26,35,43,72,87,93,106,121,128,151,160,168,193,214],"depression":[3,88,152],"is":[4,100,172,239],"great":[6],"significance":[7],"for":[8,49],"clinical":[9],"intervention.":[10],"At":[11,226],"present,":[12],"artificial":[13],"intelligence":[14],"technology":[15],"has":[16],"made":[17],"effective":[18],"progress":[19],"in":[20,153,208],"the":[21,31,37,41,70,84,91,104,113,135,142,149,157,161,164,166,169,177,186,191,194,200,217,223,227,230],"field":[22],"automatic":[24],"detection":[25,94],"depression.":[27,124],"However,":[28],"due":[29],"to":[30,82,102,109,133,139,184],"scarcity":[32],"and":[33,46,90,111,118,163,189,220,236],"homogeneity":[34],"data,":[36],"existing":[38],"models":[39,75],"have":[40],"problem":[42],"insufficient":[44],"robustness":[45,92,192],"generalization":[47],"ability":[48],"unseen":[50],"data":[51],"or":[52],"out-ofdistribution":[53],"data.":[54],"To":[55],"address":[56],"these":[57],"challenges,":[58],"this":[59],"paper":[60],"proposes":[61],"a":[62,107],"multi-strategy":[63],"collaborative":[64,158],"training":[65,159,187],"framework,":[66],"DeprGen-RL,":[67],"which":[68],"combines":[69],"advantages":[71],"large":[73,97],"language":[74,98,154],"(LLMs)":[76],"with":[77,123,148],"reinforcement":[78,129],"learning":[79,130],"(RL),":[80],"aiming":[81],"improve":[83,190],"generation":[85,137,231],"quality":[86,232],"text":[89,136,144],"models.":[95],"A":[96],"model":[99,178],"used":[101,132],"play":[103],"role":[105],"generator":[108,162,171],"learn":[110],"reproduce":[112],"unique":[114],"vocabulary,":[115],"syntactic":[116],"structure":[117],"emotional":[119],"expression":[120],"patients":[122],"The":[125],"reward":[126],"mechanism":[127],"was":[131,145],"guide":[134],"process":[138],"ensure":[140],"that":[141,176,199],"generated":[143],"highly":[146],"consistent":[147],"correlation":[150],"features.":[155],"Through":[156],"discriminator,":[165],"performance":[167],"LLM":[170],"continuously":[173],"optimized,":[174],"so":[175],"can":[179],"generate":[180],"high-quality":[181],"synthetic":[182],"texts":[183],"expand":[185],"set":[188],"downstream":[195],"classifier.":[196],"Experiments":[197],"show":[198],"DeprGen-RL":[201],"discriminator":[202],"performs":[203],"better":[204],"than":[205],"traditional":[206],"methods":[207],"cross-dataset":[209],"experiments,":[210],"achieving":[211],"an":[212],"accuracy":[213],"0.72":[215],"on":[216,222],"Pirina":[218],"dataset":[219],"0.81":[221],"DAIC-WOZ":[224],"dataset.":[225],"same":[228],"time,":[229],"(measured":[233],"by":[234],"perplexity":[235],"BLEU":[237],"value)":[238],"also":[240],"improved.":[241]},"counts_by_year":[],"updated_date":"2026-02-01T03:34:12.195049","created_date":"2026-01-30T00:00:00"}