{"id":"https://openalex.org/W7154701029","doi":"https://doi.org/10.48550/arxiv.2604.14920","title":"Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models","display_name":"Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models","publication_year":2026,"publication_date":"2026-04-16","ids":{"openalex":"https://openalex.org/W7154701029","doi":"https://doi.org/10.48550/arxiv.2604.14920"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.14920","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.14920","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.14920","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133884933","display_name":"Yifu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yifu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133909062","display_name":"Shengpeng Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Shengpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103048218","display_name":"Zhengqing Liu","orcid":"https://orcid.org/0000-0002-9553-1554"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhengqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133890451","display_name":"Qian Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133839208","display_name":"Wen J. Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133910708","display_name":"Ziqing Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ziqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073742206","display_name":"Yangzhuo Li","orcid":"https://orcid.org/0000-0003-4450-2849"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yangzhuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125996254","display_name":"Tianle Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Tianle","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133916404","display_name":"Zhou Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Zhou","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4203999936580658,"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/T10028","display_name":"Topic Modeling","score":0.4203999936580658,"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/T12031","display_name":"Speech and dialogue systems","score":0.27810001373291016,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1843000054359436,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7189000248908997},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6661999821662903},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.631600022315979},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5044999718666077},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5023000240325928},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42890000343322754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.782800018787384},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7189000248908997},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6661999821662903},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.631600022315979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.613099992275238},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5044999718666077},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4406000077724457},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42890000343322754},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28529998660087585},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.26179999113082886}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.14920","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.14920","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":"doi:10.48550/arxiv.2604.14920","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.14920","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Achieving":[0],"seamless,":[1],"human-like":[2],"interaction":[3,58,113,136],"remains":[4],"a":[5,38,49,102,116,124,149,168],"key":[6,44],"challenge":[7,45],"for":[8,30,46,56,77,132,145,155],"full-duplex":[9],"spoken":[10],"dialogue":[11],"models":[12],"(SDMs).":[13],"Reinforcement":[14],"learning":[15],"(RL)":[16],"has":[17],"substantially":[18],"enhanced":[19],"text-":[20],"and":[21,91,119,135,147,176],"vision-language":[22],"models,":[23],"while":[24],"well-designed":[25],"reward":[26,75,152],"signals":[27,76],"are":[28],"crucial":[29],"the":[31,43,80],"performance":[32,163],"of":[33,171],"RL.":[34,78],"We":[35,95],"consider":[36],"RL":[37],"promising":[39],"strategy":[40],"to":[41,72,93,110],"address":[42],"SDMs.":[47],"However,":[48],"fundamental":[50],"barrier":[51,99],"persists:":[52],"prevailing":[53],"automated":[54],"metrics":[55],"assessing":[57],"quality":[59,134],"rely":[60],"on":[61,164],"superficial":[62],"proxies,":[63],"such":[64],"as":[65],"behavioral":[66],"statistics":[67],"or":[68],"timing-prediction":[69],"accuracy,":[70],"failing":[71],"provide":[73],"reliable":[74],"On":[79],"other":[81],"hand,":[82],"human":[83],"evaluations,":[84],"despite":[85],"their":[86],"richness,":[87],"remain":[88],"costly,":[89],"inconsistent,":[90],"difficult":[92],"scale.":[94],"tackle":[96],"this":[97],"critical":[98],"by":[100],"proposing":[101],"Dual-Axis":[103],"Generative":[104],"Reward":[105],"Model,":[106],"which":[107],"is":[108],"trained":[109],"understand":[111],"complex":[112,177],"dynamics":[114],"using":[115],"detailed":[117],"taxonomy":[118],"an":[120],"annotated":[121],"dataset,":[122],"produces":[123],"single":[125],"score":[126],"and,":[127],"crucially,":[128],"provides":[129],"separate":[130],"evaluations":[131],"semantic":[133],"timing.":[137],"Such":[138],"dual":[139],"outputs":[140],"furnish":[141],"precise":[142],"diagnostic":[143],"feedback":[144],"SDMs":[146],"deliver":[148],"dependable,":[150],"instructive":[151],"signal":[153],"suitable":[154],"online":[156],"reinforcement":[157],"learning.":[158],"Our":[159],"model":[160],"achieves":[161],"state-of-the-art":[162],"interaction-quality":[165],"assessment":[166],"across":[167],"wide":[169],"spectrum":[170],"datasets,":[172],"spanning":[173],"synthetic":[174],"dialogues":[175],"real-world":[178],"interactions.":[179]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-18T00:00:00"}