{"id":"https://openalex.org/W4412889583","doi":"https://doi.org/10.18653/v1/2025.acl-long.1532","title":"Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights","display_name":"Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889583","doi":"https://doi.org/10.18653/v1/2025.acl-long.1532"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1532","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1532","pdf_url":"https://aclanthology.org/2025.acl-long.1532.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.1532.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sooyung Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sooyung Choi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070981690","display_name":"J. M. Lee","orcid":"https://orcid.org/0009-0005-5991-9163"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaehyeok Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040961637","display_name":"Xiaoyuan Yi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyuan Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113051737","display_name":"Jing Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044651577","display_name":"Xing Xie","orcid":"https://orcid.org/0000-0002-8608-8482"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xing Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044635661","display_name":"JinYeong Bak","orcid":"https://orcid.org/0000-0002-3212-5241"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"JinYeong Bak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.729,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90564321,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"31742","last_page":"31768"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10019","display_name":"Corporate Finance and Governance","score":0.8633999824523926,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10019","display_name":"Corporate Finance and Governance","score":0.8633999824523926,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/unintended-consequences","display_name":"Unintended consequences","score":0.7252687215805054},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5779423117637634},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.34666916728019714},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.33191609382629395},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.23237207531929016},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.21993118524551392}],"concepts":[{"id":"https://openalex.org/C2776889888","wikidata":"https://www.wikidata.org/wiki/Q1135789","display_name":"Unintended consequences","level":2,"score":0.7252687215805054},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5779423117637634},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.34666916728019714},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33191609382629395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.23237207531929016},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.21993118524551392},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1532","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1532","pdf_url":"https://aclanthology.org/2025.acl-long.1532.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.1532","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1532","pdf_url":"https://aclanthology.org/2025.acl-long.1532.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":[{"id":"https://openalex.org/G1610820195","display_name":null,"funder_award_id":"RS-2019-II190421","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4377996611","display_name":null,"funder_award_id":"RS-2019-II190421","funder_id":"https://openalex.org/F4320321378","funder_display_name":"Sungkyunkwan University"},{"id":"https://openalex.org/G438840348","display_name":null,"funder_award_id":"RS-2019-II190421","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320321378","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320333993","display_name":"Microsoft Research Asia","ror":"https://ror.org/0300m5276"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889583.pdf","grobid_xml":"https://content.openalex.org/works/W4412889583.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4367679432","https://openalex.org/W4248277314","https://openalex.org/W4387098652","https://openalex.org/W4380051107","https://openalex.org/W2964483883","https://openalex.org/W4283465890","https://openalex.org/W4237585931","https://openalex.org/W2092503922"],"abstract_inverted_index":{"The":[0],"application":[1],"scope":[2],"of":[3,137,149],"Large":[4],"Language":[5],"Models":[6],"(LLMs)":[7],"continues":[8],"to":[9,12,70,74,101,145],"expand,":[10],"leading":[11],"increasing":[13],"interest":[14],"in":[15,82],"personalized":[16],"LLMs":[17,51,66,96],"that":[18],"align":[19],"with":[20,26,38,49,112],"human":[21],"values.However,":[22],"aligning":[23],"these":[24,58],"models":[25,76],"individual":[27],"values":[28,35],"raises":[29],"significant":[30,118],"safety":[31,46,84,91,114,124,148],"concerns,":[32],"as":[33],"certain":[34],"may":[36],"correlate":[37],"harmful":[39,71,108],"information.In":[40],"this":[41],"paper,":[42],"we":[43,116],"identify":[44],"specific":[45],"risks":[47,81],"associated":[48],"value-aligned":[50,95,150],"and":[52,77,123,140],"investigate":[53],"the":[54,102,134,147],"psychological":[55,128],"principles":[56],"behind":[57],"challenges.Our":[59],"findings":[60],"reveal":[61],"two":[62],"key":[63],"insights.(1)":[64],"Value-aligned":[65],"are":[67],"more":[68],"prone":[69],"behavior":[72],"compared":[73],"non-fine-tuned":[75],"exhibit":[78],"slightly":[79],"higher":[80],"traditional":[83],"evaluations":[85],"than":[86],"other":[87],"fine-tuned":[88],"models.(2)":[89],"These":[90],"issues":[92],"arise":[93],"because":[94],"genuinely":[97],"generate":[98],"text":[99],"according":[100],"aligned":[103],"values,":[104],"which":[105],"can":[106],"amplify":[107],"outcomes.Using":[109],"a":[110],"dataset":[111],"detailed":[113],"categories,":[115],"find":[117],"correlations":[119],"between":[120],"value":[121,138],"alignment":[122,139,143],"risks,":[125],"supported":[126],"by":[127],"hypotheses.This":[129],"study":[130],"offers":[131],"insights":[132],"into":[133],"\"black":[135],"box\"":[136],"proposes":[141],"in-context":[142],"methods":[144],"enhance":[146],"LLMs.":[151],"1":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-23T13:55:30.953635","created_date":"2025-10-10T00:00:00"}
