{"id":"https://openalex.org/W4390188126","doi":"https://doi.org/10.1109/iit59782.2023.10366424","title":"Generating Synthetic Data from Large Language Models","display_name":"Generating Synthetic Data from Large Language Models","publication_year":2023,"publication_date":"2023-11-14","ids":{"openalex":"https://openalex.org/W4390188126","doi":"https://doi.org/10.1109/iit59782.2023.10366424"},"language":"en","primary_location":{"id":"doi:10.1109/iit59782.2023.10366424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iit59782.2023.10366424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 15th International Conference on Innovations in Information Technology (IIT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023772220","display_name":"Sunil Choenni","orcid":"https://orcid.org/0000-0003-2772-6330"},"institutions":[{"id":"https://openalex.org/I4210145896","display_name":"Ministry of Security and Justice","ror":"https://ror.org/04nzhmg91","country_code":"NL","type":"government","lineage":["https://openalex.org/I4210140876","https://openalex.org/I4210145896"]},{"id":"https://openalex.org/I907135538","display_name":"Rotterdam University of Applied Sciences","ror":"https://ror.org/0481e1q24","country_code":"NL","type":"education","lineage":["https://openalex.org/I907135538"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Sunil Choenni","raw_affiliation_strings":["Rotterdam University of Applied Sciences,Research & Documentation Center, Ministry of Justice & Security, and Research Center Creating 010,The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rotterdam University of Applied Sciences,Research & Documentation Center, Ministry of Justice & Security, and Research Center Creating 010,The Netherlands","institution_ids":["https://openalex.org/I4210145896","https://openalex.org/I907135538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076163374","display_name":"Tony Busker","orcid":"https://orcid.org/0000-0003-4731-3058"},"institutions":[{"id":"https://openalex.org/I907135538","display_name":"Rotterdam University of Applied Sciences","ror":"https://ror.org/0481e1q24","country_code":"NL","type":"education","lineage":["https://openalex.org/I907135538"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Tony Busker","raw_affiliation_strings":["Rotterdam University of Applied Sciences,Research Center Creating 010,The Netherlands","Research Center Creating 010, Rotterdam University of Applied Sciences, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rotterdam University of Applied Sciences,Research Center Creating 010,The Netherlands","institution_ids":["https://openalex.org/I907135538"]},{"raw_affiliation_string":"Research Center Creating 010, Rotterdam University of Applied Sciences, The Netherlands","institution_ids":["https://openalex.org/I907135538"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065846991","display_name":"Mortaza S. Bargh","orcid":"https://orcid.org/0000-0001-5395-456X"},"institutions":[{"id":"https://openalex.org/I4210145896","display_name":"Ministry of Security and Justice","ror":"https://ror.org/04nzhmg91","country_code":"NL","type":"government","lineage":["https://openalex.org/I4210140876","https://openalex.org/I4210145896"]},{"id":"https://openalex.org/I907135538","display_name":"Rotterdam University of Applied Sciences","ror":"https://ror.org/0481e1q24","country_code":"NL","type":"education","lineage":["https://openalex.org/I907135538"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mortaza S. Bargh","raw_affiliation_strings":["Rotterdam University of Applied Sciences,Research & Documentation Center, Ministry of Justice & Security, and Research Center Creating 010,The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rotterdam University of Applied Sciences,Research & Documentation Center, Ministry of Justice & Security, and Research Center Creating 010,The Netherlands","institution_ids":["https://openalex.org/I4210145896","https://openalex.org/I907135538"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8052,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78992224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"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":0.9986000061035156,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7641804814338684},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7158827185630798},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.7124686241149902},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5900499820709229},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.5856325626373291},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.5441421866416931},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4777609407901764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3530147075653076},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33302685618400574},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.13711625337600708},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09446755051612854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7641804814338684},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7158827185630798},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.7124686241149902},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5900499820709229},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.5856325626373291},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5441421866416931},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4777609407901764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3530147075653076},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33302685618400574},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.13711625337600708},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09446755051612854},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iit59782.2023.10366424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iit59782.2023.10366424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 15th International Conference on Innovations in Information Technology (IIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1903873348","https://openalex.org/W1904228841","https://openalex.org/W2031342017","https://openalex.org/W2109664771","https://openalex.org/W2437096199","https://openalex.org/W2753439427","https://openalex.org/W2983341525","https://openalex.org/W3081876271","https://openalex.org/W3120485916","https://openalex.org/W3199411432","https://openalex.org/W4210888287","https://openalex.org/W4245648902","https://openalex.org/W4297802254","https://openalex.org/W4323655724","https://openalex.org/W4388823861","https://openalex.org/W6743659760","https://openalex.org/W6763142499","https://openalex.org/W6770131217","https://openalex.org/W6786313011"],"related_works":["https://openalex.org/W2045155990","https://openalex.org/W4313163053","https://openalex.org/W4300973204","https://openalex.org/W3045811229","https://openalex.org/W1483408780","https://openalex.org/W2608960204","https://openalex.org/W3109499659","https://openalex.org/W4382315317","https://openalex.org/W2966641257","https://openalex.org/W4399530423"],"abstract_inverted_index":{"Data":[0],"collection":[1,29],"for":[2,60,150],"studying":[3,61,151],"social":[4,62,155],"phenomena":[5],"is":[6,11,66],"not":[7],"only":[8],"costly":[9],"but":[10],"also,":[12],"at":[13],"best,":[14],"a":[15,55,70,100,128],"time-consuming":[16],"and":[17,35,78,80,113,143],"tedious":[18],"task.":[19],"Therefore,":[20],"tools":[21],"that":[22,44,67,95],"may":[23,52],"ease":[24],"the":[25,85,104,145],"task":[26],"of":[27,73,103,127],"data":[28,59,74,86,94,105,135,146],"will":[30],"speed":[31],"up":[32],"these":[33,90],"studies":[34],"improve":[36],"their":[37],"efficiency.":[38],"In":[39],"this":[40,123],"contribution,":[41],"we":[42,131],"argue":[43],"in":[45,87,117,122],"some":[46],"cases":[47],"Large":[48],"Language":[49],"Models":[50],"(LLMs)":[51],"serve":[53],"as":[54,99],"tool":[56],"to":[57],"generate":[58],"phenomena.":[63],"The":[64,111],"rationale":[65,119],"LLMs":[68],"absorb":[69],"vast":[71],"amount":[72],"from":[75,141],"various":[76],"types":[77],"sources;":[79],"embed":[81],"(an":[82],"abstraction":[83],"of)":[84],"models.":[88],"Querying":[89],"models":[91],"generates":[92],"synthetic":[93,134],"can":[96,136,147],"be":[97,137,148],"considered":[98],"good":[101],"approximation":[102],"on":[106,154],"which":[107],"they":[108],"are":[109,120],"trained.":[110],"methodological":[112],"practical":[114],"issues":[115],"involved":[116],"our":[118],"discussed":[121],"paper.":[124],"By":[125],"means":[126],"use":[129],"case,":[130],"illustrate":[132],"how":[133,144],"generated":[138],"(or":[139],"collected)":[140],"GPT":[142],"used":[149],"stereotypical":[152],"views":[153],"groups.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-29T08:53:18.405633","created_date":"2025-10-10T00:00:00"}