{"id":"https://openalex.org/W7154472986","doi":"https://doi.org/10.48550/arxiv.2604.12851","title":"Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment","display_name":"Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment","publication_year":2026,"publication_date":"2026-04-14","ids":{"openalex":"https://openalex.org/W7154472986","doi":"https://doi.org/10.48550/arxiv.2604.12851"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2604.12851","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.12851","pdf_url":"https://arxiv.org/pdf/2604.12851","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/2604.12851","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120724266","display_name":"Bryan Chen Zhengyu Tan","orcid":"https://orcid.org/0009-0002-0428-9641","observed_orcids":["https://orcid.org/0009-0002-0428-9641"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Bryan Chen Zhengyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130367621","display_name":"Zhengyuan Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I4405255891","display_name":"CNRS@CREATE Ltd (Singapore)","ror":"https://ror.org/03hjh0h14","country_code":"SG","type":"company","lineage":["https://openalex.org/I4405255891"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Liu, Zhengyuan","raw_affiliation_strings":["A* STAR , Singapore","CNRS@CREATE , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A* STAR , Singapore","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"CNRS@CREATE , Singapore","institution_ids":["https://openalex.org/I4405255891"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040961637","display_name":"Xiaoyuan Yi","orcid":"https://orcid.org/0000-0003-2710-1613","observed_orcids":["https://orcid.org/0000-0003-2710-1613"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi, Xiaoyuan","raw_affiliation_strings":["Microsoft Research Asia (MSRA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia (MSRA)","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104631534","display_name":"Jing Yao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yao, Jing","raw_affiliation_strings":["Microsoft Research Asia (MSRA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia (MSRA)","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153515033","display_name":"Xing Xie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xie, Xing","raw_affiliation_strings":["Microsoft Research Asia (MSRA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia (MSRA)","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014190404","display_name":"Nancy F. Chen","orcid":"https://orcid.org/0000-0003-0872-5877","observed_orcids":["https://orcid.org/0000-0003-0872-5877"]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I4405255891","display_name":"CNRS@CREATE Ltd (Singapore)","ror":"https://ror.org/03hjh0h14","country_code":"SG","type":"company","lineage":["https://openalex.org/I4405255891"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen, Nancy F.","raw_affiliation_strings":["A* STAR , Singapore","CNRS@CREATE , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A* STAR , Singapore","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"CNRS@CREATE , Singapore","institution_ids":["https://openalex.org/I4405255891"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125710083","display_name":"Roy Ka-Wei Lee","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Roy Ka-Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.9208999872207642,"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":0.9208999872207642,"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/T10028","display_name":"Topic Modeling","score":0.0575999990105629,"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/T11454","display_name":"Cultural Differences and Values","score":0.0038999998942017555,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"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":0.7300000190734863},{"id":"https://openalex.org/keywords/value-alignment","display_name":"value alignment","score":0.8840000033378601},{"id":"https://openalex.org/keywords/cultural-values","display_name":"cultural values","score":0.8029999732971191},{"id":"https://openalex.org/keywords/persona-prompting","display_name":"persona prompting","score":0.7519999742507935},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.8190000057220459},{"id":"https://openalex.org/keywords/out-of-distribution-generalization","display_name":"out-of-distribution generalization","score":0.7549999952316284},{"id":"https://openalex.org/keywords/fairness","display_name":"fairness","score":0.5870000123977661},{"id":"https://openalex.org/keywords/performance-bias","display_name":"performance bias","score":0.6909999847412109},{"id":"https://openalex.org/keywords/world-values-survey","display_name":"World Values Survey","score":0.8199999928474426},{"id":"https://openalex.org/keywords/singapore","display_name":"Singapore","score":0.6190000176429749},{"id":"https://openalex.org/keywords/gpt-4","display_name":"GPT-4","score":0.6819999814033508},{"id":"https://openalex.org/keywords/value-prediction","display_name":"value prediction","score":0.3310000002384186}],"concepts":[{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.586899995803833},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5600000023841858},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.538100004196167},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4693000018596649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4634000062942505},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.4571000039577484},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C125209646","wikidata":"https://www.wikidata.org/wiki/Q1338878","display_name":"Cultural diversity","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.31940001249313354},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3183000087738037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3124000132083893},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.31029999256134033},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3089999854564667},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C2984138521","wikidata":"https://www.wikidata.org/wiki/Q194112","display_name":"Cultural values","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C2781118332","wikidata":"https://www.wikidata.org/wiki/Q430460","display_name":"Capability approach","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29440000653266907},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.28299999237060547},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.28189998865127563},{"id":"https://openalex.org/C95986675","wikidata":"https://www.wikidata.org/wiki/Q185168","display_name":"Quantitative analysis (chemistry)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C118084267","wikidata":"https://www.wikidata.org/wiki/Q26110","display_name":"Positive economics","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.2603999972343445},{"id":"https://openalex.org/C168646138","wikidata":"https://www.wikidata.org/wiki/Q11578821","display_name":"Cross-cultural","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2596000134944916},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.2572999894618988},{"id":"https://openalex.org/C100001284","wikidata":"https://www.wikidata.org/wiki/Q2248246","display_name":"Public economics","level":1,"score":0.2558000087738037},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C2992975276","wikidata":"https://www.wikidata.org/wiki/Q11042","display_name":"Cultural background","level":4,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2604.12851","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.12851","pdf_url":"https://arxiv.org/pdf/2604.12851","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.2604.12851","doi":"https://doi.org/10.48550/arxiv.2604.12851","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12851","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2604.12851","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.12851","pdf_url":"https://arxiv.org/pdf/2604.12851","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":[{"id":"https://openalex.org/G5983670494","display_name":null,"funder_award_id":"AISG-NMLP-2024-004","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7154472986.pdf","grobid_xml":"https://content.openalex.org/works/W7154472986.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7110615284","https://openalex.org/W4408443161","https://openalex.org/W4415288418","https://openalex.org/W7034960778","https://openalex.org/W7125310942","https://openalex.org/W4416872671","https://openalex.org/W7212060985","https://openalex.org/W6979315183","https://openalex.org/W4402709952","https://openalex.org/W4415153667"],"abstract_inverted_index":{"Despite":[0],"their":[1],"global":[2],"prevalence,":[3],"many":[4],"Large":[5],"Language":[6],"Models":[7],"(LLMs)":[8],"are":[9],"aligned":[10],"to":[11,84,119],"a":[12,45,78,88],"monolithic,":[13],"often":[14],"Western-centric":[15],"set":[16],"of":[17,26,39,80,90,113,166],"values.":[18],"This":[19],"paper":[20],"investigates":[21],"the":[22,35,49,56,147,161],"more":[23],"challenging":[24],"task":[25],"fine-grained":[27],"value":[28,57],"alignment:":[29],"examining":[30],"whether":[31],"LLMs":[32],"can":[33],"emulate":[34,132],"distinct":[36],"cultural":[37,168],"values":[38],"demographic":[40],"subgroups.":[41],"Using":[42],"Singapore":[43],"as":[44],"case":[46],"study":[47],"and":[48,59,86,136,163],"World":[50],"Values":[51],"Survey":[52],"(WVS),":[53],"we":[54,123],"examine":[55],"landscape":[58],"show":[60],"that":[61,94],"even":[62],"state-of-the-art":[63],"models":[64,130],"like":[65],"GPT-4.1":[66],"achieve":[67],"only":[68],"57.4%":[69],"accuracy":[70,105],"in":[71],"predicting":[72],"subgroup":[73],"modal":[74],"preferences.":[75],"We":[76,92],"construct":[77],"dataset":[79],"over":[81],"20,000":[82],"samples":[83],"train":[85],"evaluate":[87],"range":[89],"models.":[91],"demonstrate":[93],"simple":[95],"fine-tuning":[96,141],"on":[97,106],"structured":[98],"numerical":[99],"preferences":[100],"yields":[101],"substantial":[102],"gains,":[103],"improving":[104],"unseen,":[107],"out-of-distribution":[108],"subgroups":[109,150],"by":[110,153],"an":[111],"average":[112,143],"17.4%.":[114],"These":[115],"gains":[116],"partially":[117],"transfer":[118],"open-ended":[120],"generation.":[121],"However,":[122],"find":[124],"significant":[125],"pre-existing":[126],"performance":[127],"biases,":[128],"where":[129],"better":[131],"young,":[133],"male,":[134],"Chinese,":[135],"Christian":[137],"personas.":[138],"Furthermore,":[139],"while":[140],"improves":[142],"performance,":[144],"it":[145],"widens":[146],"disparity":[148],"between":[149],"when":[151],"measured":[152],"distance-aware":[154],"metrics.":[155],"Our":[156],"work":[157],"offers":[158],"insights":[159],"into":[160],"limits":[162],"fairness":[164],"implications":[165],"subgroup-level":[167],"alignment.":[169]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-04-16T00:00:00"}