{"id":"https://openalex.org/W4416035214","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.256","title":"Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling","display_name":"Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035214","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.256"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.256","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.256","pdf_url":"https://aclanthology.org/2025.findings-emnlp.256.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.256.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107951791","display_name":"Yue Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357573","display_name":"Xiaoyu Wang","orcid":"https://orcid.org/0000-0001-9411-214X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyu Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100411767","display_name":"Dan Wang","orcid":"https://orcid.org/0000-0001-6374-0418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104274609","display_name":"Zhonglin Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhonglin Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066574703","display_name":"Qing Gu","orcid":"https://orcid.org/0000-0002-5948-4690"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingqing Gu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100637767","display_name":"Teng Chen","orcid":"https://orcid.org/0000-0001-6428-7790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Teng Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004687734","display_name":"Ningyuan Xi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ningyuan Xi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068842292","display_name":"Jia Qu","orcid":"https://orcid.org/0000-0001-5729-567X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinxian Qu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035121805","display_name":"Yong Chen","orcid":"https://orcid.org/0000-0003-1691-9460"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5072289903","display_name":"Luo Ji","orcid":"https://orcid.org/0000-0002-2484-5345"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo Ji","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16773782,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4764","last_page":"4781"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.4122999906539917,"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/T12031","display_name":"Speech and dialogue systems","score":0.4122999906539917,"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/T10028","display_name":"Topic Modeling","score":0.2101999968290329,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.06759999692440033,"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/dream","display_name":"Dream","score":0.5142999887466431},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4339999854564667},{"id":"https://openalex.org/keywords/belief-system","display_name":"Belief system","score":0.325300008058548},{"id":"https://openalex.org/keywords/user-modeling","display_name":"User modeling","score":0.32030001282691956},{"id":"https://openalex.org/keywords/mental-model","display_name":"Mental model","score":0.2741999924182892}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5259000062942505},{"id":"https://openalex.org/C2781095916","wikidata":"https://www.wikidata.org/wiki/Q36348","display_name":"Dream","level":2,"score":0.5142999887466431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4408000111579895},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4339999854564667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4025999903678894},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3756999969482422},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35339999198913574},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3278999924659729},{"id":"https://openalex.org/C2994474205","wikidata":"https://www.wikidata.org/wiki/Q34394","display_name":"Belief system","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.32030001282691956},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3052000105381012},{"id":"https://openalex.org/C2982912361","wikidata":"https://www.wikidata.org/wiki/Q1851867","display_name":"Mental model","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.273499995470047}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.256","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.256","pdf_url":"https://aclanthology.org/2025.findings-emnlp.256.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.256","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.256","pdf_url":"https://aclanthology.org/2025.findings-emnlp.256.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/W4416035214.pdf","grobid_xml":"https://content.openalex.org/works/W4416035214.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"World":[0],"models":[1],"have":[2],"been":[3],"widely":[4],"utilized":[5],"in":[6],"robotics,":[7],"gaming,":[8],"and":[9,34,40,57,81,103,118,131],"autonomous":[10],"driving.However,":[11],"their":[12],"applications":[13],"to":[14,77,135],"natural":[15],"language":[16],"tasks":[17],"are":[18],"relatively":[19],"limited.In":[20],"this":[21,42,53],"paper,":[22,43],"we":[23,44,72],"construct":[24],"the":[25,58,78,86,91],"dialogue":[26,60,79,93,107,119],"world":[27,61,94,120],"model,":[28],"which":[29,50],"could":[30],"predict":[31],"future":[32],"utterances":[33],"user":[35,54],"beliefs,":[36],"including":[37],"emotion,":[38],"sentiment,":[39],"intention.In":[41],"propose":[45],"a":[46,70,127],"framework":[47],"called":[48],"DreamCUB,":[49],"shows":[51],"that":[52,90,124],"belief":[55],"modeling":[56],"entire":[59],"model":[62,95],"can":[63,96],"be":[64],"established":[65],"by":[66,84,112],"LLM":[67],"post-training.By":[68],"defining":[69],"POMDP,":[71],"apply":[73],"model-based":[74],"reinforcement":[75],"learning":[76],"system":[80],"solve":[82],"it":[83],"maximizing":[85],"information":[87],"bottleneck.Experiments":[88],"show":[89],"pretrained":[92],"achieve":[97],"state-of-theart":[98],"performances":[99],"on":[100],"emotion":[101],"classification":[102],"sentiment":[104],"identification,":[105],"while":[106],"quality":[108],"is":[109],"also":[110,132],"enhanced":[111],"joint":[113],"training":[114],"of":[115],"policy,":[116],"critic":[117],"model.Further":[121],"analysis":[122],"reveals":[123],"DreamCUB":[125],"holds":[126],"reasonable":[128],"exploration-exploitation":[129],"balance":[130],"transfers":[133],"well":[134],"out-of-domain":[136],"scenarios":[137],"such":[138],"as":[139],"empathetic":[140],"dialogues.":[141]},"counts_by_year":[],"updated_date":"2026-03-14T06:41:57.775601","created_date":"2025-11-08T00:00:00"}