{"id":"https://openalex.org/W7117469039","doi":"https://doi.org/10.1145/3714394.3756244","title":"MindChat-R0: A Large Language Model for Emotionally Supportive Dialogue through Reinforcement Learning","display_name":"MindChat-R0: A Large Language Model for Emotionally Supportive Dialogue through Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W7117469039","doi":"https://doi.org/10.1145/3714394.3756244"},"language":null,"primary_location":{"id":"doi:10.1145/3714394.3756244","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3714394.3756244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2025 ACM International Joint Conference on Pervasive and Ubiquitous Computing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5111288134","display_name":"Dong She","orcid":"https://orcid.org/0009-0007-5378-0505"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong She","raw_affiliation_strings":["South China University of Technology, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0007-5378-0505","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121482526","display_name":"Chenxu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxu Zhang","raw_affiliation_strings":["South China University of Technology, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0000-2845-8396","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066574289","display_name":"Xianrong Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianrong Yao","raw_affiliation_strings":["South China University of Technology, GuangZhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0001-1965-4499","affiliations":[{"raw_affiliation_string":"South China University of Technology, GuangZhou, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074362965","display_name":"Y. Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["South China University of Technology, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-6811-0183","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121472797","display_name":"Zhanpeng Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanpeng Jin","raw_affiliation_strings":["South China University of Technology, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-3020-3736","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90610280"],"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":"1209","last_page":"1216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.30230000615119934,"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":0.30230000615119934,"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":0.3009999990463257,"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/T10028","display_name":"Topic Modeling","score":0.18080000579357147,"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/conversation","display_name":"Conversation","score":0.7258999943733215},{"id":"https://openalex.org/keywords/empathy","display_name":"Empathy","score":0.7251999974250793},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.592199981212616},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5875999927520752},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5679000020027161},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.48669999837875366},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.36800000071525574}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7258999943733215},{"id":"https://openalex.org/C2779885105","wikidata":"https://www.wikidata.org/wiki/Q182263","display_name":"Empathy","level":2,"score":0.7251999974250793},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.6825000047683716},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.592199981212616},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5875999927520752},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5679000020027161},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.5249000191688538},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.48669999837875366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41200000047683716},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.37599998712539673},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35429999232292175},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.3393999934196472},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28349998593330383},{"id":"https://openalex.org/C3018916638","wikidata":"https://www.wikidata.org/wiki/Q752118","display_name":"Emotional support","level":3,"score":0.26649999618530273},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C134362201","wikidata":"https://www.wikidata.org/wiki/Q317309","display_name":"Mental health","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3714394.3756244","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3714394.3756244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2025 ACM International Joint Conference on Pervasive and Ubiquitous Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47077837586402893}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W3173209146","https://openalex.org/W4402670748","https://openalex.org/W4402671297","https://openalex.org/W4402671620","https://openalex.org/W4406725278"],"related_works":[],"abstract_inverted_index":{"Emotional":[0],"Support":[1],"Conversation":[2],"(ESC)":[3],"systems":[4,26],"are":[5],"critical":[6],"for":[7,107,111],"assisting":[8],"individuals":[9],"facing":[10],"mental":[11],"health":[12],"challenges.":[13],"In":[14,113],"this":[15],"work,":[16],"we":[17,47,64],"present":[18],"a":[19,36,51,71,123],"reinforcement":[20,77],"learning":[21,78],"framework":[22],"to":[23],"improve":[24],"ESC":[25],"through":[27],"structured":[28,52],"emotional":[29,45],"reasoning.":[30],"We":[31],"first":[32],"collect":[33],"and":[34,59,102,109],"clean":[35],"dataset":[37],"of":[38,94,97,126],"4,500":[39],"real-world":[40],"support-seeking":[41],"posts.":[42],"To":[43],"guide":[44],"generation,":[46],"introduce":[48],"Empathetic":[49],"Chain-of-Thought(ECoT),":[50],"reasoning":[53],"format":[54],"that":[55,87],"encourages":[56],"multi-turn":[57],"empathy":[58],"coherence.":[60],"Based":[61],"on":[62,129],"this,":[63],"train":[65],"MindChat-R0":[66,117],"(Qwen3-8B":[67],"as":[68],"basic":[69],"model),":[70],"Chinese":[72],"empathetic":[73],"dialogue":[74],"agent,":[75],"using":[76],"optimized":[79],"by":[80,132],"ECoT-driven":[81],"reward":[82],"signals.":[83],"LLM-as-a-judge":[84],"evaluation":[85],"shows":[86],"MindChat":[88],"achieves":[89],"the":[90],"highest":[91],"average":[92],"score":[93],"3.863":[95],"out":[96],"5.0":[98],"across":[99],"fluency,":[100],"empathy,":[101],"support":[103],"dimensions":[104],"(vs.":[105],"2.834":[106],"Qwen3-8B-nothink":[108],"2.547":[110],"Qwen3-8B-think).":[112],"human":[114,133],"preference":[115],"evaluation,":[116],"also":[118],"outperforms":[119],"strong":[120],"baselines":[121],"with":[122],"win":[124],"rate":[125],"71.14%,":[127],"based":[128],"pairwise":[130],"comparisons":[131],"annotators.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-12-29T00:00:00"}