{"id":"https://openalex.org/W4416035924","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.70","title":"Flexible Thinking for Multimodal Emotional Support Conversation via Reinforcement Learning","display_name":"Flexible Thinking for Multimodal Emotional Support Conversation via Reinforcement Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035924","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.70"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.70","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.70","pdf_url":"https://aclanthology.org/2025.findings-emnlp.70.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.70.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043764949","display_name":"Fanfan Wang","orcid":"https://orcid.org/0000-0002-8955-9411"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanfan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028086891","display_name":"Xiangqing Shen","orcid":"https://orcid.org/0000-0002-9825-7853"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangqing Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084990301","display_name":"Jianfei Yu","orcid":"https://orcid.org/0000-0001-8380-0609"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianfei Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5022494657","display_name":"Rui Xia","orcid":"https://orcid.org/0000-0003-2409-1181"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Xia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6645,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90461049,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1341","last_page":"1356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.3716999888420105,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.3716999888420105,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.0820000022649765,"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/T12031","display_name":"Speech and dialogue systems","score":0.06599999964237213,"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":0.6754000186920166},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4269999861717224},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.3855000138282776},{"id":"https://openalex.org/keywords/conversation-analysis","display_name":"Conversation analysis","score":0.3840999901294708},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.335099995136261}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6754000186920166},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.6050000190734863},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.48240000009536743},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4269999861717224},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C2780829048","wikidata":"https://www.wikidata.org/wiki/Q1624720","display_name":"Conversation analysis","level":3,"score":0.3840999901294708},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3310999870300293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3303000032901764},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.31679999828338623},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31540000438690186},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.28439998626708984},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C187029079","wikidata":"https://www.wikidata.org/wiki/Q958679","display_name":"Cognitive reframing","level":2,"score":0.2712000012397766}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.70","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.70","pdf_url":"https://aclanthology.org/2025.findings-emnlp.70.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.70","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.70","pdf_url":"https://aclanthology.org/2025.findings-emnlp.70.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035924.pdf","grobid_xml":"https://content.openalex.org/works/W4416035924.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Emotional":[0],"Support":[1],"Conversation":[2],"(ESC)":[3],"systems":[4],"aim":[5],"to":[6,45,80,120],"alleviate":[7],"user":[8],"distress.However,":[9],"current":[10],"Chain-of-Thought":[11],"based":[12],"ESC":[13],"methods":[14],"often":[15],"employ":[16],"rigid,":[17],"text-only":[18],"reasoning,":[19],"limiting":[20],"adaptability":[21],"in":[22,143],"dynamic,":[23],"multimodal":[24,41],"interactions":[25],"and":[26,56,135,141],"introducing":[27],"reasoning":[28],"noise":[29],"that":[30],"degrades":[31],"support":[32,147],"quality.To":[33],"address":[34],"this,":[35],"we":[36,89],"introduce":[37],"\"Flexible":[38],"Thinking\"":[39],"for":[40,84,98,104],"ESC,":[42],"enabling":[43],"models":[44],"adaptively":[46],"select":[47],"contextually":[48],"relevant":[49],"thinking":[50,67,118],"aspects:":[51],"Visual":[52],"Scene,":[53],"Emotion,":[54],"Situation,":[55],"Response":[57],"Strategy.We":[58],"first":[59],"construct":[60],"training":[61,87],"data":[62],"by":[63],"manually":[64],"curating":[65],"flexible":[66],"demonstrations":[68],"on":[69,133],"the":[70,85],"MESC":[71,134],"dataset,":[72],"then":[73],"using":[74],"a":[75,92],"Multimodal":[76],"Large":[77],"Language":[78],"Model":[79],"synthesize":[81],"these":[82],"processes":[83,119],"full":[86],"set.Then,":[88],"propose":[90],"FIRES,":[91],"framework":[93],"integrating":[94],"Supervised":[95],"Fine-Tuning":[96],"(SFT)":[97],"initial":[99],"learning":[100],"with":[101],"Reinforcement":[102],"Learning":[103],"refinement.This":[105],"two-stage":[106],"approach":[107],"helps":[108],"FIRES":[109],"transcend":[110],"SFT's":[111],"generalization":[112],"limits":[113],"and,":[114],"crucially,":[115],"directly":[116],"links":[117],"response":[121],"quality":[122],"via":[123],"tailored":[124],"rewards,":[125],"moving":[126],"beyond":[127],"imitating":[128],"potentially":[129],"imperfect":[130],"synthetic":[131],"data.Experiments":[132],"EMOTyDA":[136],"datasets":[137],"demonstrate":[138],"FIRES's":[139],"effectiveness":[140],"generalizability":[142],"fostering":[144],"higher-quality":[145],"emotional":[146],"responses":[148],"through":[149],"adaptive":[150],"reasoning.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}