{"id":"https://openalex.org/W4389925940","doi":"https://doi.org/10.48550/arxiv.2312.10007","title":"Faithful Persona-based Conversational Dataset Generation with Large Language Models","display_name":"Faithful Persona-based Conversational Dataset Generation with Large Language Models","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4389925940","doi":"https://doi.org/10.48550/arxiv.2312.10007"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2312.10007","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.10007","pdf_url":"https://arxiv.org/pdf/2312.10007","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2312.10007","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044399159","display_name":"Pegah Jandaghi","orcid":"https://orcid.org/0000-0002-8567-8077","observed_orcids":["https://orcid.org/0000-0002-8567-8077"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jandaghi, Pegah","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020328955","display_name":"Xianghai Sheng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng, XiangHai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018174137","display_name":"Xinyi Bai","orcid":"https://orcid.org/0000-0002-1565-4344","observed_orcids":["https://orcid.org/0000-0002-1565-4344"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Xinyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073443117","display_name":"Jay Pujara","orcid":"https://orcid.org/0000-0001-6921-1744","observed_orcids":["https://orcid.org/0000-0001-6921-1744"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pujara, Jay","raw_affiliation_strings":["Information Sciences Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041538187","display_name":"Hakim Sidahmed","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sidahmed, Hakim","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":43,"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/T12031","display_name":"Speech and dialogue systems","score":0.9955999851226807,"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":0.9955999851226807,"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":0.0015999999595806003,"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/T12128","display_name":"AI in Service Interactions","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1406","display_name":"Marketing"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/synthetic-dialogue-data","display_name":"synthetic dialogue data","score":0.6259999871253967},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8119999766349792},{"id":"https://openalex.org/keywords/chatbot-personality","display_name":"chatbot personality","score":0.45100000500679016},{"id":"https://openalex.org/keywords/turing-test","display_name":"Turing test","score":0.8669999837875366}],"concepts":[{"id":"https://openalex.org/C313442","wikidata":"https://www.wikidata.org/wiki/Q778556","display_name":"Persona","level":2,"score":0.9503881931304932},{"id":"https://openalex.org/C2779041454","wikidata":"https://www.wikidata.org/wiki/Q870780","display_name":"Chatbot","level":2,"score":0.8286288976669312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7305272221565247},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5622302293777466},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4286070466041565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42443087697029114},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4201318323612213},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4169886112213135},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38239502906799316},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37041711807250977},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.18275988101959229},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2312.10007","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.10007","pdf_url":"https://arxiv.org/pdf/2312.10007","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2312.10007","doi":"https://doi.org/10.48550/arxiv.2312.10007","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.10007","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2312.10007","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.10007","pdf_url":"https://arxiv.org/pdf/2312.10007","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389925940.pdf","grobid_xml":"https://content.openalex.org/works/W4389925940.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2615146352"],"related_works":["https://openalex.org/W4386566609","https://openalex.org/W4390962269","https://openalex.org/W4405469852","https://openalex.org/W2965718149","https://openalex.org/W4394610386","https://openalex.org/W6949894138","https://openalex.org/W4417438248","https://openalex.org/W4399181308","https://openalex.org/W7131893699","https://openalex.org/W6979323934"],"abstract_inverted_index":{"High-quality":[0],"conversational":[1,59,90],"datasets":[2],"are":[3],"essential":[4],"for":[5],"developing":[6],"AI":[7],"models":[8,48,60],"that":[9,34,61,132,183],"can":[10,56],"communicate":[11],"with":[12,66],"users.":[13],"One":[14],"way":[15],"to":[16,58,85,102,120,151,197],"foster":[17],"deeper":[18,64],"interactions":[19],"between":[20],"a":[21,50,63,87,93,98,127],"chatbot":[22],"and":[23,41,52,69,171,181],"its":[24,112],"user":[25],"is":[26,116],"through":[27,178],"personas,":[28],"aspects":[29],"of":[30,80,111,126,129,136,159,169,187],"the":[31,67,78,104,109,134,137,143,153,167,184],"user's":[32],"character":[33],"provide":[35],"insights":[36],"into":[37],"their":[38,71],"personality,":[39],"motivations,":[40],"behaviors.":[42],"Training":[43],"Natural":[44],"Language":[45,82],"Processing":[46],"(NLP)":[47],"on":[49,175],"diverse":[51],"comprehensive":[53],"persona-based":[54],"dataset":[55,91],"lead":[57],"create":[62,86],"connection":[65],"user,":[68],"maintain":[70],"engagement.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76,148],"leverage":[77],"power":[79],"Large":[81],"Models":[83],"(LLMs)":[84],"large,":[88],"high-quality":[89],"from":[92,163,195],"seed":[94],"dataset.":[95],"We":[96,155,165],"propose":[97],"Generator-Critic":[99],"architecture":[100],"framework":[101,174],"expand":[103],"initial":[105],"dataset,":[106],"while":[107],"improving":[108],"quality":[110,135,168],"conversations.":[113,122,139],"The":[114,123],"Generator":[115],"an":[117],"LLM":[118],"prompted":[119],"output":[121],"Critic":[124],"consists":[125],"mixture":[128],"expert":[130],"LLMs":[131],"control":[133],"generated":[138,145],"These":[140],"experts":[141],"select":[142],"best":[144],"conversations,":[146],"which":[147],"then":[149],"use":[150],"improve":[152],"Generator.":[154],"release":[156],"Synthetic-Persona-Chat,":[157],"consisting":[158],"20k":[160],"conversations":[161],"seeded":[162],"Persona-Chat.":[164],"evaluate":[166],"Synthetic-Persona-Chat":[170,188],"our":[172],"generation":[173],"different":[176],"dimensions":[177],"extensive":[179],"experiments,":[180],"observe":[182],"losing":[185],"rate":[186],"against":[189],"Persona-Chat":[190],"during":[191],"Turing":[192],"test":[193],"decreases":[194],"17.2%":[196],"8.8%":[198],"over":[199],"three":[200],"iterations.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":12}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-12-19T00:00:00"}