{"id":"https://openalex.org/W4417117910","doi":"https://doi.org/10.48550/arxiv.2506.06404","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":"2025-06-06","ids":{"openalex":"https://openalex.org/W4417117910","doi":"https://doi.org/10.48550/arxiv.2506.06404"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.06404","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.06404","pdf_url":"https://arxiv.org/pdf/2506.06404","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.06404","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Choi, Sooyung","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Choi, Sooyung","raw_affiliation_strings":[],"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":"Lee, Jaehyeok","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040961637","display_name":"Xiaoyuan Yi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi, Xiaoyuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113051737","display_name":"Jing Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Jing","raw_affiliation_strings":[],"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":"Xie, Xing","raw_affiliation_strings":[],"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":"Bak, JinYeong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"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/T10028","display_name":"Topic Modeling","score":0.29760000109672546,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.29760000109672546,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.13009999692440033,"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":0.08349999785423279,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/unintended-consequences","display_name":"Unintended consequences","score":0.6013000011444092},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5831000208854675},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.5490999817848206},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4162999987602234},{"id":"https://openalex.org/keywords/human-factors-and-ergonomics","display_name":"Human factors and ergonomics","score":0.4052000045776367},{"id":"https://openalex.org/keywords/poison-control","display_name":"Poison control","score":0.367000013589859},{"id":"https://openalex.org/keywords/empirical-evidence","display_name":"Empirical evidence","score":0.36559998989105225}],"concepts":[{"id":"https://openalex.org/C2776889888","wikidata":"https://www.wikidata.org/wiki/Q1135789","display_name":"Unintended consequences","level":2,"score":0.6013000011444092},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5831000208854675},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5490999817848206},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.47189998626708984},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4138999879360199},{"id":"https://openalex.org/C166735990","wikidata":"https://www.wikidata.org/wiki/Q1750812","display_name":"Human factors and ergonomics","level":3,"score":0.4052000045776367},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3732999861240387},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C75630572","wikidata":"https://www.wikidata.org/wiki/Q538904","display_name":"Applied psychology","level":1,"score":0.31139999628067017},{"id":"https://openalex.org/C526869908","wikidata":"https://www.wikidata.org/wiki/Q3298118","display_name":"Suicide prevention","level":3,"score":0.3107999861240387},{"id":"https://openalex.org/C190385971","wikidata":"https://www.wikidata.org/wiki/Q373494","display_name":"Injury prevention","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C187155963","wikidata":"https://www.wikidata.org/wiki/Q629029","display_name":"Occupational safety and health","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C2777363581","wikidata":"https://www.wikidata.org/wiki/Q15098235","display_name":"Harm","level":2,"score":0.26159998774528503}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.06404","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.06404","pdf_url":"https://arxiv.org/pdf/2506.06404","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.06404","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.06404","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.06404","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.06404","pdf_url":"https://arxiv.org/pdf/2506.06404","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"application":[1],"scope":[2],"of":[3,144,156],"Large":[4],"Language":[5],"Models":[6],"(LLMs)":[7],"continues":[8],"to":[9,12,74,78,106,152],"expand,":[10],"leading":[11],"increasing":[13],"interest":[14],"in":[15,86],"personalized":[16],"LLMs":[17,53,70,101],"that":[18],"align":[19],"with":[20,27,39,51,118],"human":[21],"values.":[22],"However,":[23],"aligning":[24],"these":[25,60],"models":[26,80],"individual":[28],"values":[29,36],"raises":[30],"significant":[31,124],"safety":[32,48,88,96,120,130,155],"concerns,":[33],"as":[34],"certain":[35],"may":[37],"correlate":[38],"harmful":[40,75,113],"information.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,122],"identify":[46],"specific":[47],"risks":[49,85],"associated":[50],"value-aligned":[52,100,157],"and":[54,81,129,147],"investigate":[55],"the":[56,107,141,154],"psychological":[57,134],"principles":[58],"behind":[59],"challenges.":[61],"Our":[62],"findings":[63],"reveal":[64],"two":[65],"key":[66],"insights.":[67],"(1)":[68],"Value-aligned":[69],"are":[71],"more":[72],"prone":[73],"behavior":[76],"compared":[77],"non-fine-tuned":[79],"exhibit":[82],"slightly":[83],"higher":[84],"traditional":[87],"evaluations":[89],"than":[90],"other":[91],"fine-tuned":[92],"models.":[93],"(2)":[94],"These":[95],"issues":[97],"arise":[98],"because":[99],"genuinely":[102],"generate":[103],"text":[104],"according":[105],"aligned":[108],"values,":[109],"which":[110],"can":[111],"amplify":[112],"outcomes.":[114],"Using":[115],"a":[116],"dataset":[117],"detailed":[119],"categories,":[121],"find":[123],"correlations":[125],"between":[126],"value":[127,145],"alignment":[128,146,150],"risks,":[131],"supported":[132],"by":[133],"hypotheses.":[135],"This":[136],"study":[137],"offers":[138],"insights":[139],"into":[140],"\"black":[142],"box\"":[143],"proposes":[148],"in-context":[149],"methods":[151],"enhance":[153],"LLMs.":[158]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}