{"id":"https://openalex.org/W4412944944","doi":"https://doi.org/10.18653/v1/2025.acl-long.999","title":"BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data","display_name":"BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944944","doi":"https://doi.org/10.18653/v1/2025.acl-long.999"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.999","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.999","pdf_url":"https://aclanthology.org/2025.acl-long.999.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.999.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009530693","display_name":"Wenkai Li","orcid":"https://orcid.org/0000-0001-6548-7882"},"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":"Wenkai Li","raw_affiliation_strings":["Language Technologies Institute , Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute , Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042386588","display_name":"Jiarui Liu","orcid":"https://orcid.org/0009-0008-2090-5145"},"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":"Jiarui Liu","raw_affiliation_strings":["Language Technologies Institute , Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute , Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035499719","display_name":"Andy Liu","orcid":"https://orcid.org/0009-0003-6173-143X"},"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":"Andy Liu","raw_affiliation_strings":["Language Technologies Institute , Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute , Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003775059","display_name":"Xuhui Zhou","orcid":"https://orcid.org/0000-0002-2038-9901"},"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":"Xuhui Zhou","raw_affiliation_strings":["Language Technologies Institute , Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute , Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038581447","display_name":"Mona Diab","orcid":"https://orcid.org/0000-0002-7696-1436"},"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":"Mona T. Diab","raw_affiliation_strings":["Language Technologies Institute , Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute , Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015128745","display_name":"Maarten Sap","orcid":"https://orcid.org/0000-0002-0701-4654"},"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":"Maarten Sap","raw_affiliation_strings":["Language Technologies Institute , Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute , Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20434","last_page":"20471"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.9731000065803528,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"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/T13643","display_name":"Artificial Intelligence in Law","score":0.9731000065803528,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.916700005531311,"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/training","display_name":"Training (meteorology)","score":0.5737413763999939},{"id":"https://openalex.org/keywords/personality-psychology","display_name":"Personality psychology","score":0.5660991072654724},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5308873057365417},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3465460538864136},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23709586262702942},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10120627284049988},{"id":"https://openalex.org/keywords/personality","display_name":"Personality","score":0.09794551134109497}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5737413763999939},{"id":"https://openalex.org/C25908422","wikidata":"https://www.wikidata.org/wiki/Q271716","display_name":"Personality psychology","level":3,"score":0.5660991072654724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5308873057365417},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3465460538864136},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23709586262702942},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10120627284049988},{"id":"https://openalex.org/C187288502","wikidata":"https://www.wikidata.org/wiki/Q641118","display_name":"Personality","level":2,"score":0.09794551134109497},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.999","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.999","pdf_url":"https://aclanthology.org/2025.acl-long.999.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.999","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.999","pdf_url":"https://aclanthology.org/2025.acl-long.999.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944944.pdf","grobid_xml":"https://content.openalex.org/works/W4412944944.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2351143970","https://openalex.org/W606758982","https://openalex.org/W2356968146","https://openalex.org/W2292633468","https://openalex.org/W2377676319","https://openalex.org/W230091440","https://openalex.org/W2048396937"],"abstract_inverted_index":{"In":[0],"this":[1,62,140],"work,":[2],"we":[3,41,64],"tackle":[4],"the":[5,24,28,143],"challenge":[6],"of":[7],"embedding":[8],"realistic":[9],"human":[10,81,101,135,160],"personality":[11,30,59,82,88],"traits":[12,133],"into":[13],"LLMs.Previous":[14],"approaches":[15],"have":[16],"primarily":[17],"focused":[18],"on":[19,87,123,130],"prompt-based":[20],"methods":[21,74,84,151],"that":[22,106],"describe":[23],"behavior":[25],"associated":[26],"with":[27,80,95,127],"desired":[29],"traits,":[31],"suffering":[32],"from":[33,158],"realism":[34],"and":[35,68,93,117],"validity":[36],"issues.To":[37],"address":[38],"these":[39,132],"limitations,":[40],"introduce":[42],"BIG5-CHAT,":[43],"a":[44],"large-scale":[45],"dataset":[46],"containing":[47],"100,000":[48],"dialogues":[49],"designed":[50],"to":[51,75,109,147],"ground":[52],"models":[53,107],"in":[54,60],"how":[55,131,149],"humans":[56],"express":[57],"their":[58],"language.Leveraging":[61],"dataset,":[63],"explore":[65],"Supervised":[66],"Fine-Tuning":[67],"Direct":[69],"Preference":[70],"Optimization":[71],"as":[72,91],"training-based":[73,150],"align":[76],"LLMs":[77],"more":[78,98],"naturally":[79],"patterns.Our":[83],"outperform":[85],"prompting":[86],"assessments":[89],"such":[90],"BFI":[92],"IPIP-NEO,":[94],"trait":[96],"correlations":[97],"closely":[99],"matching":[100],"data.Furthermore,":[102],"our":[103,138],"experiments":[104],"reveal":[105],"trained":[108],"exhibit":[110],"higher":[111,113],"conscientiousness,":[112],"agreeableness,":[114],"lower":[115,118],"extraversion,":[116],"neuroticism":[119],"display":[120],"better":[121],"performance":[122],"reasoning":[124],"tasks,":[125],"aligning":[126],"psychological":[128],"findings":[129],"impact":[134],"cognitive":[136],"performance.To":[137],"knowledge,":[139],"work":[141],"is":[142],"first":[144],"comprehensive":[145],"study":[146],"demonstrate":[148],"can":[152],"shape":[153],"LLM":[154],"personalities":[155],"through":[156],"learning":[157],"real":[159],"behaviors.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}