{"id":"https://openalex.org/W4415088231","doi":"https://doi.org/10.48550/arxiv.2509.11362","title":"PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits","display_name":"PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits","publication_year":2025,"publication_date":"2025-09-14","ids":{"openalex":"https://openalex.org/W4415088231","doi":"https://doi.org/10.48550/arxiv.2509.11362"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.11362","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.11362","pdf_url":"https://arxiv.org/pdf/2509.11362","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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/2509.11362","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101307847","display_name":"Loka Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Loka","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119958775","display_name":"Wong Yu Kang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kang, Wong Yu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fu, Minghao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fu, Minghao","raw_affiliation_strings":["University of California San Diego ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego ,","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088257057","display_name":"Guangyi Chen","orcid":"https://orcid.org/0000-0001-7542-5378","observed_orcids":["https://orcid.org/0000-0001-7542-5378","https://orcid.org/0000-0002-4811-2402"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Guangyi","raw_affiliation_strings":["University of Artificial Intelligence ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Artificial Intelligence ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106669775","display_name":"Zhenhao Chen","orcid":"https://orcid.org/0009-0004-0560-728X","observed_orcids":["https://orcid.org/0009-0004-0560-728X"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Zhenhao","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012997528","display_name":"Gongxu Luo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luo, Gongxu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103266231","display_name":"Yuewen Sun","orcid":"https://orcid.org/0000-0001-7534-1297","observed_orcids":["https://orcid.org/0000-0001-7534-1297"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yuewen","raw_affiliation_strings":["University of Artificial Intelligence ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Artificial Intelligence ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101483978","display_name":"Salman Khan","orcid":"https://orcid.org/0000-0001-8732-3395","observed_orcids":["https://orcid.org/0000-0001-8732-3395"]},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Khan, Salman","raw_affiliation_strings":["Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047533473","display_name":"Peter Spirtes","orcid":"https://orcid.org/0000-0002-1385-190X","observed_orcids":["https://orcid.org/0000-0002-1385-190X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Spirtes, Peter","raw_affiliation_strings":["University of Artificial Intelligence ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Artificial Intelligence ,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100342309","display_name":"Kun Zhang","orcid":"https://orcid.org/0000-0002-0738-9958","observed_orcids":["https://orcid.org/0000-0002-0738-9958"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Kun","raw_affiliation_strings":["University of Artificial Intelligence ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Artificial Intelligence ,","institution_ids":[]}]}],"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":1,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.38670000433921814,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.38670000433921814,"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"}},{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.08250000327825546,"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/T11040","display_name":"Personality Traits and Psychology","score":0.05979999899864197,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical 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/behavioral-characteristics","display_name":"behavioral characteristics","score":0.5590000152587891},{"id":"https://openalex.org/keywords/multimodal-dataset","display_name":"multimodal dataset","score":0.7910000085830688},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7839999794960022},{"id":"https://openalex.org/keywords/public-figures","display_name":"public figures","score":0.8220000267028809},{"id":"https://openalex.org/keywords/professional-athletes","display_name":"professional athletes","score":0.9810000061988831},{"id":"https://openalex.org/keywords/facial-attributes","display_name":"facial attributes","score":0.9049999713897705},{"id":"https://openalex.org/keywords/biographical-information","display_name":"biographical information","score":0.9179999828338623},{"id":"https://openalex.org/keywords/causal-representation-learning","display_name":"causal representation learning","score":0.9589999914169312},{"id":"https://openalex.org/keywords/identifiability","display_name":"identifiability","score":0.6899999976158142}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6642000079154968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6087999939918518},{"id":"https://openalex.org/C106934330","wikidata":"https://www.wikidata.org/wiki/Q1971873","display_name":"Trait","level":2,"score":0.6018999814987183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5343000292778015},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.5019999742507935},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4397999942302704},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42739999294281006},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4196000099182129},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3465000092983246},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33149999380111694},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3246000111103058},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26030001044273376},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.11362","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.11362","pdf_url":"https://arxiv.org/pdf/2509.11362","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.11362","doi":"https://doi.org/10.48550/arxiv.2509.11362","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.11362","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:2509.11362","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.11362","pdf_url":"https://arxiv.org/pdf/2509.11362","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415088231.pdf","grobid_xml":"https://content.openalex.org/works/W4415088231.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4362679380","https://openalex.org/W4415537956","https://openalex.org/W4406514140","https://openalex.org/W7214699512","https://openalex.org/W3095255024","https://openalex.org/W4416936928","https://openalex.org/W7168138516","https://openalex.org/W7171863779","https://openalex.org/W7125486501","https://openalex.org/W4409346343"],"abstract_inverted_index":{"Understanding":[0],"human":[1],"behavior":[2],"traits":[3,71,194],"is":[4,211],"central":[5],"to":[6,25,65,140,158],"applications":[7],"in":[8,195],"human-computer":[9],"interaction,":[10],"computational":[11],"social":[12],"science,":[13],"and":[14,29,48,86,114,134,160,171,183,199,206],"personalized":[15],"AI":[16],"systems.":[17],"Such":[18],"understanding":[19],"often":[20],"requires":[21],"integrating":[22],"multiple":[23],"modalities":[24,43],"capture":[26],"nuanced":[27],"patterns":[28],"relationships.":[30],"However,":[31],"existing":[32],"resources":[33],"rarely":[34],"provide":[35],"datasets":[36,63],"that":[37],"combine":[38],"behavioral":[39,101,193],"descriptors":[40],"with":[41,144,197],"complementary":[42,123],"such":[44],"as":[45],"facial":[46,112],"attributes":[47],"biographical":[49,116,200],"information.":[50],"To":[51],"address":[52],"this":[53],"gap,":[54],"we":[55,126,148],"present":[56],"PersonaX,":[57],"a":[58,150,188],"curated":[59],"collection":[60],"of":[61,69,76,177],"multimodal":[62,159,203],"designed":[64],"enable":[66],"comprehensive":[67],"analysis":[68,205],"public":[70,81],"across":[72,93],"modalities.":[73,146],"PersonaX":[74,120,186],"consists":[75],"(1)":[77],"CelebPersona,":[78],"featuring":[79],"9444":[80],"figures":[82],"from":[83,131],"diverse":[84],"occupations,":[85],"(2)":[87],"AthlePersona,":[88],"covering":[89],"4181":[90],"professional":[91],"athletes":[92],"7":[94],"major":[95],"sports":[96],"leagues.":[97],"Each":[98],"dataset":[99],"includes":[100],"trait":[102,129,204],"assessments":[103],"inferred":[104],"by":[105],"three":[106],"high-performing":[107],"large":[108],"language":[109],"models,":[110],"alongside":[111],"imagery":[113],"structured":[115,182],"features.":[117],"We":[118],"analyze":[119],"at":[121,213],"two":[122],"levels.":[124],"First,":[125],"abstract":[127],"high-level":[128],"scores":[130],"text":[132],"descriptions":[133],"apply":[135],"five":[136],"statistical":[137],"independence":[138],"tests":[139],"examine":[141],"their":[142],"relationships":[143],"other":[145],"Second,":[147],"introduce":[149],"novel":[151],"causal":[152,207],"representation":[153],"learning":[154],"(CRL)":[155],"framework":[156],"tailored":[157],"multi-measurement":[161],"data,":[162],"providing":[163],"theoretical":[164],"identifiability":[165],"guarantees.":[166],"Experiments":[167],"on":[168],"both":[169],"synthetic":[170],"real-world":[172],"data":[173],"demonstrate":[174],"the":[175],"effectiveness":[176],"our":[178],"approach.":[179],"By":[180],"unifying":[181],"unstructured":[184],"analysis,":[185],"establishes":[187],"foundation":[189],"for":[190],"studying":[191],"LLM-inferred":[192],"conjunction":[196],"visual":[198],"attributes,":[201],"advancing":[202],"reasoning.":[208],"The":[209],"code":[210],"available":[212],"https://github.com/lokali/PersonaX.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-10-12T00:00:00"}