{"id":"https://openalex.org/W7152459389","doi":"https://doi.org/10.48550/arxiv.2604.06663","title":"Restoring Heterogeneity in LLM-based Social Simulation: An Audience Segmentation Approach","display_name":"Restoring Heterogeneity in LLM-based Social Simulation: An Audience Segmentation Approach","publication_year":2026,"publication_date":"2026-04-08","ids":{"openalex":"https://openalex.org/W7152459389","doi":"https://doi.org/10.48550/arxiv.2604.06663"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.06663","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06663","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":null,"license_id":null,"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.2604.06663","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133292820","display_name":"Xiaoyou Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Xiaoyou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389148","display_name":"Zhihong Li","orcid":"https://orcid.org/0000-0001-6802-6731"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhihong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103183184","display_name":"Xiaoxiao Cheng","orcid":"https://orcid.org/0000-0002-0354-6928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Xiaoxiao","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/T13910","display_name":"Computational and Text Analysis Methods","score":0.34130001068115234,"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"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.34130001068115234,"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"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.06970000267028809,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.033799998462200165,"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/segmentation","display_name":"Segmentation","score":0.70660001039505},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5364000201225281},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.5228000283241272},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.49709999561309814},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.46959999203681946},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.45329999923706055},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4293000102043152},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.4253999888896942},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.38960000872612},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.38659998774528503}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.70660001039505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.660099983215332},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5364000201225281},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5314000248908997},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.5228000283241272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5164999961853027},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.49709999561309814},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.46959999203681946},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4253999888896942},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C2776493592","wikidata":"https://www.wikidata.org/wiki/Q5158717","display_name":"Succinctness","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3747999966144562},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.06663","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06663","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.06663","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06663","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.8485376834869385,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"used":[6],"to":[7,39],"simulate":[8],"social":[9,40,56,215],"attitudes":[10],"and":[11,74,82,87,101,127,131,149,180,190,217,224],"behaviors,":[12],"offering":[13],"scalable":[14],"\"silicon":[15],"samples\"":[16],"that":[17,36,106],"can":[18,117,128,196],"approximate":[19],"human":[20],"data.":[21],"However,":[22],"current":[23],"simulation":[24,91,216],"practice":[25],"often":[26,139],"collapses":[27],"diversity":[28],"into":[29],"an":[30],"\"average":[31],"persona,\"":[32],"masking":[33],"subgroup":[34],"variation":[35],"is":[37],"central":[38],"reality.":[41],"This":[42],"study":[43],"introduces":[44],"audience":[45,205],"segmentation":[46,66,78,206],"as":[47,207],"a":[48,94,208],"systematic":[49],"approach":[50,211],"for":[51,212,221],"restoring":[52],"heterogeneity":[53],"in":[54,147,193,200],"LLM-based":[55,214],"simulation.":[57],"Using":[58],"U.S.":[59],"climate-opinion":[60],"survey":[61],"data,":[62],"we":[63],"compare":[64],"six":[65],"configurations":[67,138],"across":[68],"two":[69],"open-weight":[70],"LLMs":[71],"(Llama":[72],"3.1-70B":[73],"Mixtral":[75],"8x22B),":[76],"varying":[77],"identifier":[79,108],"granularity,":[80],"parsimony,":[81],"selection":[83,159,168,175],"logic":[84,160],"(theory-driven,":[85],"data-driven,":[86],"instrument-based).":[88],"We":[89],"evaluate":[90],"performance":[92,191],"with":[93,198],"three-dimensional":[95],"evaluation":[96,223],"framework":[97],"covering":[98],"distributional,":[99],"structural,":[100],"predictive":[102,132,150],"fidelity.":[103,133],"Results":[104],"show":[105],"increasing":[107],"granularity":[109],"does":[110,123],"not":[111,124],"produce":[112],"consistent":[113],"improvement:":[114],"moderate":[115],"enrichment":[116],"improve":[118],"performance,":[119],"but":[120],"further":[121],"expansion":[122],"reliably":[125],"help":[126],"worsen":[129],"structural":[130,148],"Across":[134],"parsimony":[135],"comparisons,":[136],"compact":[137],"match":[140],"or":[141],"outperform":[142],"more":[143],"comprehensive":[144],"alternatives,":[145],"especially":[146],"fidelity,":[151],"while":[152],"distributional":[153,171],"fidelity":[154,163],"remains":[155],"metric":[156],"dependent.":[157],"Identifier":[158],"determines":[161],"which":[162],"dimension":[164,195],"benefits":[165],"most:":[166],"instrument-based":[167],"best":[169,176],"preserves":[170],"shape,":[172],"whereas":[173],"data-driven":[174],"recovers":[177],"between-group":[178],"structure":[179],"identifier-outcome":[181],"associations.":[182],"Overall,":[183],"no":[184],"single":[185],"configuration":[186],"dominates":[187],"all":[188],"dimensions,":[189],"gains":[192],"one":[194],"coincide":[197],"losses":[199],"another.":[201],"These":[202],"findings":[203],"position":[204],"core":[209],"methodological":[210],"valid":[213],"highlight":[218],"the":[219],"need":[220],"heterogeneity-aware":[222],"variance-preserving":[225],"modeling":[226],"strategies.":[227]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-10T00:00:00"}