{"id":"https://openalex.org/W7120178595","doi":"https://doi.org/10.48550/arxiv.2601.04436","title":"Learning to Simulate Human Dialogue","display_name":"Learning to Simulate Human Dialogue","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7120178595","doi":"https://doi.org/10.48550/arxiv.2601.04436"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2601.04436","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.04436","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.2601.04436","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122600372","display_name":"Kanishk Gandhi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gandhi, Kanishk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122496377","display_name":"Agam Bhatia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhatia, Agam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5122546287","display_name":"Noah D. Goodman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goodman, Noah D.","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":0.412200003862381,"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":0.412200003862381,"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":0.16760000586509705,"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":0.06270000338554382,"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/utterance","display_name":"Utterance","score":0.645799994468689},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.48919999599456787},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.45680001378059387},{"id":"https://openalex.org/keywords/completeness","display_name":"Completeness (order theory)","score":0.426800012588501},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.3490999937057495},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.32600000500679016}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.645799994468689},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.57669997215271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5224000215530396},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.48919999599456787},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37700000405311584},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33649998903274536},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3212999999523163},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.28220000863075256},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2601.04436","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.04436","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.2601.04436","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.04436","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":{"To":[0],"predict":[1,22,152],"what":[2,153],"someone":[3],"will":[4],"say":[5],"is":[6,41,51,125,130],"to":[7,43,65,99,132,150,213],"model":[8,40,129,148],"how":[9,49],"they":[10],"think.":[11],"We":[12,30,80],"study":[13],"this":[14,180,211],"through":[15,54],"next-turn":[16],"dialogue":[17],"prediction:":[18],"given":[19],"a":[20,28,118,168,173,200,221],"conversation,":[21],"the":[23,39,66,73,76,96,106,113,128,141,147,177,183],"next":[24],"utterance":[25],"produced":[26],"by":[27,70,138],"person.":[29],"compare":[31],"learning":[32,50],"approaches":[33],"along":[34],"two":[35],"dimensions:":[36],"(1)":[37],"whether":[38],"allowed":[42,131],"think":[44,133],"before":[45,134],"responding,":[46],"and":[47,61,104,120,161,208],"(2)":[48],"rewarded":[52],"either":[53],"an":[55],"LLM-as-a-judge":[56],"that":[57,82,193,209],"scores":[58,90],"semantic":[59],"similarity":[60],"information":[62],"completeness":[63],"relative":[64],"ground-truth":[67],"response,":[68],"or":[69],"directly":[71,139],"maximizing":[72,140],"log-probability":[74,142,160],"of":[75,143,225],"true":[77],"human":[78,102,110,145,206,226],"dialogue.":[79],"find":[81],"optimizing":[83],"for":[84],"judge-based":[85],"rewards":[86],"indeed":[87],"increases":[88],"judge":[89],"throughout":[91],"training,":[92],"however":[93],"it":[94],"decreases":[95,105],"likelihood":[97],"assigned":[98],"ground":[100],"truth":[101],"responses":[103],"win":[107,162],"rate":[108,163],"when":[109,127,197],"judges":[111],"choose":[112],"most":[114],"human-like":[115],"response":[116],"among":[117],"real":[119,205],"synthetic":[121],"option.":[122],"This":[123],"failure":[124],"amplified":[126],"answering.":[135],"In":[136],"contrast,":[137],"observed":[144],"responses,":[146],"learns":[149],"better":[151],"people":[154],"actually":[155],"say,":[156],"improving":[157],"on":[158,176,186],"both":[159],"evaluations.":[164,189],"Treating":[165],"chain-of-thought":[166],"as":[167],"latent":[169],"variable,":[170],"we":[171],"derive":[172],"lower":[174],"bound":[175],"log-probability.":[178],"Optimizing":[179],"objective":[181,202],"yields":[182],"best":[184],"results":[185,191],"all":[187],"our":[188],"These":[190],"suggest":[192],"thinking":[194],"helps":[195],"primarily":[196],"trained":[198],"with":[199,220],"distribution-matching":[201],"grounded":[203],"in":[204],"dialogue,":[207],"scaling":[210],"approach":[212],"broader":[214],"conversational":[215],"data":[216],"may":[217],"produce":[218],"models":[219],"more":[222],"nuanced":[223],"understanding":[224],"behavior.":[227]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-01-10T00:00:00"}