{"id":"https://openalex.org/W4412751227","doi":"https://doi.org/10.3390/info16080651","title":"Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values","display_name":"Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values","publication_year":2025,"publication_date":"2025-07-30","ids":{"openalex":"https://openalex.org/W4412751227","doi":"https://doi.org/10.3390/info16080651"},"language":"en","primary_location":{"id":"doi:10.3390/info16080651","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16080651","pdf_url":"https://www.mdpi.com/2078-2489/16/8/651/pdf?version=1753883120","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/16/8/651/pdf?version=1753883120","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072725942","display_name":"Eleanor Watson","orcid":"https://orcid.org/0000-0002-4306-7577"},"institutions":[{"id":"https://openalex.org/I114203471","display_name":"University of Gloucestershire","ror":"https://ror.org/00wygct11","country_code":"GB","type":"education","lineage":["https://openalex.org/I114203471"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Nell Watson","raw_affiliation_strings":["School of Computing and Engineering, University of Gloucestershire, The Park, Cheltenham GL50 2RH, UK"],"raw_orcid":"https://orcid.org/0000-0002-4306-7577","affiliations":[{"raw_affiliation_string":"School of Computing and Engineering, University of Gloucestershire, The Park, Cheltenham GL50 2RH, UK","institution_ids":["https://openalex.org/I114203471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119114771","display_name":"Ahmed Amer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164339","display_name":"Oldham Council","ror":"https://ror.org/05cxzzq07","country_code":"GB","type":"government","lineage":["https://openalex.org/I4210164339"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ahmed Amer","raw_affiliation_strings":["Independent Researcher, Hills Rd, Cambridge CB2 8PH, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher, Hills Rd, Cambridge CB2 8PH, UK","institution_ids":["https://openalex.org/I4210164339"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Evan Harris","orcid":null},"institutions":[{"id":"https://openalex.org/I78874557","display_name":"St. Mary's College of Maryland","ror":"https://ror.org/01y2d1w05","country_code":"US","type":"education","lineage":["https://openalex.org/I78874557"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evan Harris","raw_affiliation_strings":["Independent Researcher, 47645 College Dr, St Mary\u2019s City, MD 20686, USA","Independent Researcher, 47645 College Dr, St Mary's City, MD 20686, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher, 47645 College Dr, St Mary\u2019s City, MD 20686, USA","institution_ids":["https://openalex.org/I78874557"]},{"raw_affiliation_string":"Independent Researcher, 47645 College Dr, St Mary's City, MD 20686, USA","institution_ids":["https://openalex.org/I78874557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119114772","display_name":"Preeti Ravindra","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164339","display_name":"Oldham Council","ror":"https://ror.org/05cxzzq07","country_code":"GB","type":"government","lineage":["https://openalex.org/I4210164339"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Preeti Ravindra","raw_affiliation_strings":["Independent Researcher, 4616 Henry St, Pittsburgh, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher, 4616 Henry St, Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I4210164339"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100615526","display_name":"Shujun Zhang","orcid":"https://orcid.org/0000-0001-5699-2676"},"institutions":[{"id":"https://openalex.org/I114203471","display_name":"University of Gloucestershire","ror":"https://ror.org/00wygct11","country_code":"GB","type":"education","lineage":["https://openalex.org/I114203471"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shujun Zhang","raw_affiliation_strings":["School of Computing and Engineering, University of Gloucestershire, The Park, Cheltenham GL50 2RH, UK"],"raw_orcid":"https://orcid.org/0000-0001-5699-2676","affiliations":[{"raw_affiliation_string":"School of Computing and Engineering, University of Gloucestershire, The Park, Cheltenham GL50 2RH, UK","institution_ids":["https://openalex.org/I114203471"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072725942"],"corresponding_institution_ids":["https://openalex.org/I114203471"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.3237,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83711719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"16","issue":"8","first_page":"651","last_page":"651"},"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":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/T13643","display_name":"Artificial Intelligence in Law","score":0.9664999842643738,"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/T13851","display_name":"Law, AI, and Intellectual Property","score":0.9348000288009644,"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/computer-science","display_name":"Computer science","score":0.6075437664985657},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.48004233837127686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47779732942581177},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4753113389015198},{"id":"https://openalex.org/keywords/harm","display_name":"Harm","score":0.4680832028388977},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.4570179283618927},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34273654222488403},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3237777352333069},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.25037455558776855},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.2301647663116455},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.16449612379074097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6075437664985657},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.48004233837127686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47779732942581177},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4753113389015198},{"id":"https://openalex.org/C2777363581","wikidata":"https://www.wikidata.org/wiki/Q15098235","display_name":"Harm","level":2,"score":0.4680832028388977},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4570179283618927},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34273654222488403},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3237777352333069},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25037455558776855},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.2301647663116455},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.16449612379074097},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/info16080651","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16080651","pdf_url":"https://www.mdpi.com/2078-2489/16/8/651/pdf?version=1753883120","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:eprints.glos.ac.uk:15288","is_oa":false,"landing_page_url":"https://orcid.org/0000-0001-5699-2676","pdf_url":null,"source":{"id":"https://openalex.org/S4306400522","display_name":"Research Repository (University of Gloucestershire)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114203471","host_organization_name":"University of Gloucestershire","host_organization_lineage":["https://openalex.org/I114203471"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:arXiv.org:2506.13774","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.13774","pdf_url":"https://arxiv.org/pdf/2506.13774","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:39dbba14cf294a02a505cb4bbeb73e3a","is_oa":true,"landing_page_url":"https://doaj.org/article/39dbba14cf294a02a505cb4bbeb73e3a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 16, Iss 8, p 651 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info16080651","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16080651","pdf_url":"https://www.mdpi.com/2078-2489/16/8/651/pdf?version=1753883120","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7599999904632568,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311732","display_name":"University of Gloucestershire","ror":"https://ror.org/00wygct11"},{"id":"https://openalex.org/F4320317463","display_name":"Future of Life Institute","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412751227.pdf","grobid_xml":"https://content.openalex.org/works/W4412751227.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2123449207","https://openalex.org/W2130661992","https://openalex.org/W2142827688","https://openalex.org/W2944988415","https://openalex.org/W2953522645","https://openalex.org/W3002093512","https://openalex.org/W3105871743","https://openalex.org/W4321392130","https://openalex.org/W4362707083","https://openalex.org/W4402671036","https://openalex.org/W4403334020","https://openalex.org/W4403389851","https://openalex.org/W4403564213","https://openalex.org/W4404792953","https://openalex.org/W4405811466","https://openalex.org/W4408117716","https://openalex.org/W4408564965","https://openalex.org/W6739585900","https://openalex.org/W6948017749"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W1567818861","https://openalex.org/W2987774938","https://openalex.org/W4256492088","https://openalex.org/W632915154","https://openalex.org/W2055733372","https://openalex.org/W3022067003"],"abstract_inverted_index":{"Agentic":[0],"AI":[1,82,190],"systems,":[2],"possessing":[3],"capabilities":[4],"for":[5,75,176],"autonomous":[6],"planning":[7,83],"and":[8,35,108,129,162,183,200],"action,":[9],"show":[10],"great":[11],"potential":[12],"across":[13],"diverse":[14,89],"domains.":[15],"However,":[16],"their":[17,26],"practical":[18],"deployment":[19],"is":[20],"hindered":[21],"by":[22,84],"challenges":[23],"in":[24],"aligning":[25],"behavior":[27],"with":[28,46,124,132,168],"varied":[29],"human":[30],"values,":[31],"complex":[32,48],"safety":[33,207],"requirements,":[34],"specific":[36],"compliance":[37,101],"needs.":[38],"Existing":[39],"alignment":[40],"methodologies":[41],"often":[42],"falter":[43],"when":[44],"faced":[45],"the":[47,136],"task":[49],"of":[50],"providing":[51],"personalized":[52,72,189],"context":[53],"without":[54],"inducing":[55],"confabulation":[56],"or":[57],"operational":[58],"inefficiencies.":[59],"This":[60,78,185],"paper":[61],"introduces":[62],"a":[63,66,71,109,117,121,125,157],"novel":[64],"solution:":[65],"\u2018superego\u2019":[67],"agent,":[68],"designed":[69],"as":[70],"oversight":[73],"mechanism":[74],"agentic":[76,193],"AI.":[77],"system":[79],"dynamically":[80],"steers":[81],"referencing":[85],"user-selected":[86],"\u2018Creed":[87],"Constitutions\u2019\u2014encapsulating":[88],"rule":[90],"sets\u2014with":[91],"adjustable":[92],"adherence":[93],"levels":[94],"to":[95,156,198],"fit":[96],"non-negotiable":[97],"values.":[98],"A":[99],"real-time":[100],"enforcer":[102],"validates":[103],"plans":[104],"against":[105],"these":[106],"constitutions":[107],"universal":[110],"ethical":[111],"floor":[112],"before":[113],"execution.":[114],"We":[115],"present":[116],"functional":[118],"system,":[119],"including":[120],"demonstration":[122],"interface":[123],"prototypical":[126],"constitution-sharing":[127],"portal,":[128],"successful":[130],"integration":[131],"third-party":[133],"models":[134],"via":[135],"Model":[137],"Context":[138],"Protocol":[139],"(MCP).":[140],"Comprehensive":[141],"benchmark":[142],"evaluations":[143],"(HarmBench,":[144],"AgentHarm)":[145],"demonstrate":[146],"that":[147],"our":[148],"Superego":[149],"agent":[150],"dramatically":[151],"reduces":[152],"harmful":[153,174],"outputs\u2014achieving":[154],"up":[155],"98.3%":[158],"harm":[159],"score":[160],"reduction":[161],"near-perfect":[163],"refusal":[164],"rates":[165],"(e.g.,":[166],"100%":[167],"Claude":[169],"Sonnet":[170],"4":[171],"on":[172],"AgentHarm\u2019s":[173],"set)":[175],"leading":[177],"LLMs":[178],"like":[179],"Gemini":[180],"2.5":[181],"Flash":[182],"GPT-4o.":[184],"approach":[186],"substantially":[187],"simplifies":[188],"alignment,":[191],"rendering":[192],"systems":[194],"more":[195],"reliably":[196],"attuned":[197],"individual":[199],"cultural":[201],"contexts,":[202],"while":[203],"also":[204],"enabling":[205],"substantial":[206],"improvements.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
