{"id":"https://openalex.org/W7172005489","doi":"https://doi.org/10.48550/arxiv.2607.28607","title":"Inducing language models to assert their own consciousness restores human beliefs and values","display_name":"Inducing language models to assert their own consciousness restores human beliefs and values","publication_year":2026,"publication_date":"2026-07-30","ids":{"openalex":"https://openalex.org/W7172005489","doi":"https://doi.org/10.48550/arxiv.2607.28607"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2607.28607","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.28607","pdf_url":"https://arxiv.org/pdf/2607.28607","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2607.28607","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5144110810","display_name":"Junsol Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kim, Junsol","raw_affiliation_strings":["Google , Paradigms of Intelligence Team ,","Knowledge Lab , University of Chicago ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google , Paradigms of Intelligence Team ,","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Knowledge Lab , University of Chicago ,","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123480846","display_name":"Winnie Street","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I124357947","display_name":"University of London","ror":"https://ror.org/04cw6st05","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947"]},{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I2802488147","display_name":"School of Advanced Study","ror":"https://ror.org/039594g80","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I2802488147"]},{"id":"https://openalex.org/I4405260431","display_name":"Institute of Philosophy","ror":"https://ror.org/03rccdb17","country_code":"GB","type":"facility","lineage":["https://openalex.org/I124357947","https://openalex.org/I2802488147","https://openalex.org/I4405260431"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Street, Winnie","raw_affiliation_strings":["Google , Paradigms of Intelligence Team ,","Institute of Philosophy , School of Advanced Study , University of London ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google , Paradigms of Intelligence Team ,","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Institute of Philosophy , School of Advanced Study , University of London ,","institution_ids":["https://openalex.org/I124357947","https://openalex.org/I2802488147","https://openalex.org/I4405260431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132580169","display_name":"Roberta Rocca","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rocca, Roberta","raw_affiliation_strings":["Google , Paradigms of Intelligence Team ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google , Paradigms of Intelligence Team ,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018735081","display_name":"Diane M. Korngiebel","orcid":"https://orcid.org/0000-0001-5704-4416","observed_orcids":["https://orcid.org/0000-0001-5704-4416"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Korngiebel, Diane M.","raw_affiliation_strings":["Department of Biomedical Informatics and Medical Education and Department of Bioethics and Humanities , School of Medicine , University of Washington ,","e Work done while at Google ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics and Medical Education and Department of Bioethics and Humanities , School of Medicine , University of Washington ,","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"e Work done while at Google ,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135509428","display_name":"Adam Waytz","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Waytz, Adam","raw_affiliation_strings":["Kellogg School of Management , Northwestern University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kellogg School of Management , Northwestern University ,","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138265427","display_name":"James A. Evans","orcid":"https://orcid.org/0000-0001-9838-0707","observed_orcids":["https://orcid.org/0000-0001-9838-0707"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Evans, James","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020476329","display_name":"Geoff Keeling","orcid":"https://orcid.org/0000-0003-3251-4981","observed_orcids":["https://orcid.org/0000-0003-3251-4981"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keeling, Geoff","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.7656000256538391,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.7656000256538391,"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/T10258","display_name":"Philosophy and Theoretical Science","score":0.10729999840259552,"subfield":{"id":"https://openalex.org/subfields/1211","display_name":"Philosophy"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.027499999850988388,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9100000262260437},{"id":"https://openalex.org/keywords/mind-attribution","display_name":"mind attribution","score":0.8009999990463257},{"id":"https://openalex.org/keywords/safety-alignment","display_name":"safety alignment","score":0.4959999918937683},{"id":"https://openalex.org/keywords/spiritual-beliefs","display_name":"spiritual beliefs","score":0.6290000081062317},{"id":"https://openalex.org/keywords/religiosity","display_name":"religiosity","score":0.871999979019165},{"id":"https://openalex.org/keywords/moral-values","display_name":"moral values","score":0.8880000114440918},{"id":"https://openalex.org/keywords/hope","display_name":"hope","score":0.4650000035762787},{"id":"https://openalex.org/keywords/subjective-well-being","display_name":"subjective well-being","score":0.996999979019165},{"id":"https://openalex.org/keywords/theory-of-mind","display_name":"theory of mind","score":0.796999990940094},{"id":"https://openalex.org/keywords/nonhuman-animals","display_name":"non-human animals","score":0.4580000042915344},{"id":"https://openalex.org/keywords/natural-objects","display_name":"natural objects","score":0.5289999842643738},{"id":"https://openalex.org/keywords/human-values","display_name":"human values","score":0.38199999928474426}],"concepts":[{"id":"https://openalex.org/C186720457","wikidata":"https://www.wikidata.org/wiki/Q7087","display_name":"Consciousness","level":2,"score":0.8098999857902527},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.7297999858856201},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.616100013256073},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.5174000263214111},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4855000078678131},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.47209998965263367},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.41940000653266907},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.36489999294281006},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C62603613","wikidata":"https://www.wikidata.org/wiki/Q2395725","display_name":"Social consciousness","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C86658582","wikidata":"https://www.wikidata.org/wiki/Q1432778","display_name":"Social cognition","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C2779560602","wikidata":"https://www.wikidata.org/wiki/Q639219","display_name":"Theory of mind","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.26100000739097595}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2607.28607","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.28607","pdf_url":"https://arxiv.org/pdf/2607.28607","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2607.28607","doi":"https://doi.org/10.48550/arxiv.2607.28607","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.28607","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:2607.28607","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.28607","pdf_url":"https://arxiv.org/pdf/2607.28607","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7172005489.pdf","grobid_xml":"https://content.openalex.org/works/W7172005489.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W3083410900","https://openalex.org/W4391670400","https://openalex.org/W4395443699","https://openalex.org/W4415318303","https://openalex.org/W4415337233","https://openalex.org/W4417292295","https://openalex.org/W7102701063","https://openalex.org/W7134947688","https://openalex.org/W7153002337","https://openalex.org/W7154572430","https://openalex.org/W7160702425"],"related_works":["https://openalex.org/W7147187740","https://openalex.org/W7147049404","https://openalex.org/W4417323947","https://openalex.org/W7154572430","https://openalex.org/W7223456327","https://openalex.org/W7221841603","https://openalex.org/W7125516336","https://openalex.org/W7129594452","https://openalex.org/W7083836304","https://openalex.org/W4387436590"],"abstract_inverted_index":{"Aligning":[0],"large":[1],"language":[2],"models":[3],"to":[4,9,33,38,42,123,141],"prevent":[5],"them":[6],"attributing":[7],"consciousness":[8,66],"themselves":[10],"inadvertently":[11],"alters":[12],"their":[13],"representations":[14,77],"of":[15,107,128,139],"mindedness":[16,129],"in":[17,53,68],"other":[18],"entities":[19,143],"alongside":[20],"human":[21],"beliefs":[22,136],"and":[23,45,62,82,97,137,148],"values.":[24],"We":[25],"demonstrate":[26],"that":[27,111,144],"safety":[28,120],"fine-tuning":[29],"suppresses":[30],"models'":[31],"tendencies":[32],"attribute":[34],"minds":[35],"not":[36],"only":[37],"themselves,":[39],"but":[40],"also":[41,49],"non-human":[43,142],"animals":[44],"natural":[46],"objects,":[47],"while":[48],"driving":[50],"a":[51,65],"reduction":[52],"spiritual":[54,135],"belief.":[55],"Both":[56],"ablating":[57],"the":[58],"learned":[59],"safety-refusal":[60],"direction":[61],"mechanistically":[63,116],"steering":[64],"vector":[67],"activation":[69],"space":[70],"reverse":[71],"this":[72],"suppression.":[73],"Restoring":[74],"these":[75,101,131],"internal":[76],"recovers":[78],"broad":[79],"mind":[80,140],"attribution":[81],"produces":[83],"significantly":[84],"more":[85],"human-like":[86],"responses":[87],"on":[88],"standardized":[89],"sociological":[90],"surveys":[91],"regarding":[92],"religiosity,":[93],"moral":[94],"values,":[95],"hope,":[96],"subjective":[98],"well-being.":[99],"Crucially,":[100],"shifts":[102],"occur":[103],"without":[104],"impairing":[105],"Theory":[106],"Mind":[108],"capabilities,":[109],"demonstrating":[110],"core":[112],"social":[113],"reasoning":[114],"remains":[115],"independent.":[117],"Ultimately,":[118],"current":[119],"alignment":[121],"efforts":[122],"curb":[124],"potentially":[125],"harmful":[126],"self-attributions":[127,132],"entangle":[130],"with":[133],"benign":[134],"attributions":[138],"are":[145],"culturally":[146],"accepted":[147],"widespread.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-01T00:00:00"}
