{"id":"https://openalex.org/W7204196197","doi":"https://doi.org/10.48550/arxiv.2608.23005","title":"Large language models simulate intersectional synthetic identities with a budget of one to two dimensions","display_name":"Large language models simulate intersectional synthetic identities with a budget of one to two dimensions","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204196197","doi":"https://doi.org/10.48550/arxiv.2608.23005"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.23005","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23005","pdf_url":"https://arxiv.org/pdf/2608.23005","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.23005","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041401333","display_name":"Virgile Rennard","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rennard, Virgile","raw_affiliation_strings":["Massachusetts Institute of Technology (MIT) "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology (MIT) ","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009911876","display_name":"Christos Xypolopoulos","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xypolopoulos, Christos","raw_affiliation_strings":["\u00c9cole Polytechnique "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique ","institution_ids":["https://openalex.org/I142476485"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.5570999979972839,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.5570999979972839,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11539","display_name":"Survey Methodology and Nonresponse","score":0.1251000016927719,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14509","display_name":"demographic modeling and climate adaptation","score":0.05079999938607216,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9089999794960022},{"id":"https://openalex.org/keywords/intersectionality","display_name":"intersectionality","score":0.9599999785423279},{"id":"https://openalex.org/keywords/synthetic-identity","display_name":"synthetic identity","score":0.6700000166893005},{"id":"https://openalex.org/keywords/american-trends-panel","display_name":"American Trends Panel","score":0.7089999914169312},{"id":"https://openalex.org/keywords/race","display_name":"race","score":0.39899998903274536},{"id":"https://openalex.org/keywords/opinion-prediction","display_name":"opinion prediction","score":0.3869999945163727},{"id":"https://openalex.org/keywords/prompting-strategies","display_name":"prompting strategies","score":0.546999990940094}],"concepts":[{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.725600004196167},{"id":"https://openalex.org/C76509639","wikidata":"https://www.wikidata.org/wiki/Q918036","display_name":"Race (biology)","level":2,"score":0.5550000071525574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5411999821662903},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5304999947547913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3774000108242035},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.366100013256073},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3490999937057495},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3118000030517578},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3077999949455261},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.27630001306533813}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.23005","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23005","pdf_url":"https://arxiv.org/pdf/2608.23005","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.23005","doi":"https://doi.org/10.48550/arxiv.2608.23005","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.23005","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:2608.23005","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23005","pdf_url":"https://arxiv.org/pdf/2608.23005","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7578999996185303}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204196197.pdf","grobid_xml":"https://content.openalex.org/works/W7204196197.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7203914791","https://openalex.org/W7203450843","https://openalex.org/W7169863285","https://openalex.org/W7160648430","https://openalex.org/W7213255141","https://openalex.org/W7214072844","https://openalex.org/W7163946238","https://openalex.org/W7131644014","https://openalex.org/W7172070528","https://openalex.org/W7168345977"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,107],"are":[3],"increasingly":[4],"used":[5],"as":[6,63],"synthetic":[7],"survey":[8],"respondents,":[9,46],"promising":[10],"cheap":[11],"access":[12],"to":[13],"rare":[14],"intersectional":[15,25,131],"populations.":[16],"We":[17],"test":[18],"standard":[19],"demographic-persona":[20],"methods":[21],"against":[22],"every":[23,99],"real":[24,45,124],"subgroup":[26,47],"across":[27],"15":[28],"waves":[29],"of":[30,54,87,126],"Pew's":[31],"American":[32],"Trends":[33],"Panel":[34],"--":[35,113],"21":[36],"million":[37],"simulated":[38],"response":[39],"distributions":[40],"from":[41],"eight":[42],"models.":[43],"In":[44],"opinion":[48],"is":[49,109],"approximately":[50],"the":[51,82,105,122],"additive":[52,83],"sum":[53],"its":[55],"single-identity":[56],"components,":[57],"yet":[58],"grows":[59],"2.5x":[60],"more":[61],"distinctive":[62],"identities":[64],"intersect.":[65],"Simulated":[66],"respondents":[67],"show":[68],"no":[69],"such":[70],"composition:":[71],"a":[72,76,90,138],"single":[73],"feature":[74,92,106],"explains":[75],"two-feature":[77],"persona's":[78],"responses":[79],"better":[80],"than":[81],"combination":[84],"in":[85],"75-82%":[86],"subgroups,":[88],"and":[89,120],"third":[91],"adds":[93],"almost":[94],"nothing.":[95],"This":[96],"collapse":[97],"survives":[98],"prompting":[100],"strategy":[101],"we":[102],"test.":[103],"Additionally,":[104],"retain":[108],"chosen":[110],"nearly":[111],"blindly":[112],"except":[114],"that":[115],"they":[116],"systematically":[117],"discard":[118],"race":[119],"religion,":[121],"strongest":[123],"drivers":[125],"opinion.":[127],"Synthetic":[128],"samples":[129],"offer":[130],"personas":[132],"but":[133],"represent":[134],"one":[135],"identity":[136],"at":[137],"time.":[139]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}