{"id":"https://openalex.org/W4399363436","doi":"https://doi.org/10.1145/3630106.3658979","title":"Collective Constitutional AI: Aligning a Language Model with Public Input","display_name":"Collective Constitutional AI: Aligning a Language Model with Public Input","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4399363436","doi":"https://doi.org/10.1145/3630106.3658979"},"language":"en","primary_location":{"id":"doi:10.1145/3630106.3658979","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3658979","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658979","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658979","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040949100","display_name":"Saffron Huang","orcid":"https://orcid.org/0009-0008-2654-5961"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Saffron Huang","raw_affiliation_strings":["Collective Intelligence Project, USA"],"raw_orcid":"https://orcid.org/0009-0008-2654-5961","affiliations":[{"raw_affiliation_string":"Collective Intelligence Project, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020987927","display_name":"Divya Siddarth","orcid":"https://orcid.org/0009-0006-7073-6728"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Divya Siddarth","raw_affiliation_strings":["Collective Intelligence Project, USA"],"raw_orcid":"https://orcid.org/0009-0006-7073-6728","affiliations":[{"raw_affiliation_string":"Collective Intelligence Project, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047846683","display_name":"Liane Lovitt","orcid":"https://orcid.org/0009-0001-2105-5612"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liane Lovitt","raw_affiliation_strings":["Anthropic, USA"],"raw_orcid":"https://orcid.org/0009-0001-2105-5612","affiliations":[{"raw_affiliation_string":"Anthropic, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058639265","display_name":"Thomas I. Liao","orcid":"https://orcid.org/0009-0002-3936-1391"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas I. Liao","raw_affiliation_strings":["Unaffiliated, USA"],"raw_orcid":"https://orcid.org/0009-0002-3936-1391","affiliations":[{"raw_affiliation_string":"Unaffiliated, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001994692","display_name":"Esin Durmus","orcid":"https://orcid.org/0009-0009-7331-8160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Esin Durmus","raw_affiliation_strings":["Anthropic, USA"],"raw_orcid":"https://orcid.org/0009-0009-7331-8160","affiliations":[{"raw_affiliation_string":"Anthropic, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081558429","display_name":"Alex Tamkin","orcid":"https://orcid.org/0009-0006-0007-3746"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Tamkin","raw_affiliation_strings":["Anthropic, USA"],"raw_orcid":"https://orcid.org/0009-0006-0007-3746","affiliations":[{"raw_affiliation_string":"Anthropic, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006294201","display_name":"Deep Ganguli","orcid":"https://orcid.org/0009-0007-9435-3817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deep Ganguli","raw_affiliation_strings":["Anthropic, USA"],"raw_orcid":"https://orcid.org/0009-0007-9435-3817","affiliations":[{"raw_affiliation_string":"Anthropic, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5040949100"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.923,"has_fulltext":true,"cited_by_count":56,"citation_normalized_percentile":{"value":0.99356324,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1395","last_page":"1417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9521999955177307,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9521999955177307,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9302999973297119,"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/T10028","display_name":"Topic Modeling","score":0.9251000285148621,"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/cognitive-reframing","display_name":"Cognitive reframing","score":0.830281674861908},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6704464554786682},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6365832686424255},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6262036561965942},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5904635190963745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4727631211280823},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4213183522224426},{"id":"https://openalex.org/keywords/agent-based-model","display_name":"Agent-based model","score":0.41679060459136963},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3378172516822815},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33476144075393677},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21257439255714417},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.16119486093521118},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.15710213780403137},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.1477298140525818}],"concepts":[{"id":"https://openalex.org/C187029079","wikidata":"https://www.wikidata.org/wiki/Q958679","display_name":"Cognitive reframing","level":2,"score":0.830281674861908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6704464554786682},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6365832686424255},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6262036561965942},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5904635190963745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4727631211280823},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4213183522224426},{"id":"https://openalex.org/C2780873155","wikidata":"https://www.wikidata.org/wiki/Q392811","display_name":"Agent-based model","level":2,"score":0.41679060459136963},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3378172516822815},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33476144075393677},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21257439255714417},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.16119486093521118},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.15710213780403137},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.1477298140525818},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3630106.3658979","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3658979","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658979","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.07814","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.07814","pdf_url":"https://arxiv.org/pdf/2406.07814","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3630106.3658979","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3658979","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658979","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399363436.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1512597729","https://openalex.org/W1607035479","https://openalex.org/W2013784666","https://openalex.org/W2302703641","https://openalex.org/W2995006168","https://openalex.org/W3041006571","https://openalex.org/W3133874049","https://openalex.org/W3172415559","https://openalex.org/W3174220540","https://openalex.org/W3175060421","https://openalex.org/W4225006216","https://openalex.org/W4226278401","https://openalex.org/W4234208591","https://openalex.org/W4253763531","https://openalex.org/W4283161771","https://openalex.org/W4283170666","https://openalex.org/W4287116904","https://openalex.org/W4287674181","https://openalex.org/W4309618902","https://openalex.org/W4377372266","https://openalex.org/W4377823230","https://openalex.org/W4380319885","https://openalex.org/W4380365635","https://openalex.org/W4388007985","https://openalex.org/W6782465632"],"related_works":["https://openalex.org/W2061896288","https://openalex.org/W1965599462","https://openalex.org/W2025581759","https://openalex.org/W2256481674","https://openalex.org/W2011143448","https://openalex.org/W2417845289","https://openalex.org/W2944195030","https://openalex.org/W3118029303","https://openalex.org/W4383617227","https://openalex.org/W2121272715"],"abstract_inverted_index":{"There":[0],"is":[1],"growing":[2],"consensus":[3],"that":[4,23,36,153,177],"language":[5,198],"model":[6,100,104,124,172],"(LM)":[7],"developers":[8],"should":[9],"not":[10],"be":[11],"the":[12,25,31,75,88,122,134,150,154,158,170,179],"sole":[13],"deciders":[14],"of":[15,33,78,119,149,160,183,197],"LM":[16,34,90,111],"behavior,":[17],"creating":[18,82],"a":[19,49,61,71,102,110,184,189],"need":[20],"for":[21,52],"methods":[22],"enable":[24],"broader":[26],"public":[27,56,95],"to":[28,64,67,85,133,174],"collectively":[29,93],"shape":[30],"behavior":[32],"systems":[35],"affect":[37],"them.":[38],"To":[39],"address":[40],"this":[41,79,99],"need,":[42],"we":[43],"present":[44],"Collective":[45],"Constitutional":[46],"AI":[47],"(CCAI):":[48],"multi-stage":[50],"process":[51],"sourcing":[53,65],"and":[54,69,97,144],"integrating":[55],"input":[57,96],"into":[58],"LMs\u2014from":[59],"identifying":[60],"target":[62],"population":[63],"principles":[66,108],"training":[68],"evaluating":[70,98],"model.":[72],"We":[73],"demonstrate":[74,116,188],"real-world":[76],"practicality":[77],"approach":[80],"by":[81],"what":[83],"is,":[84],"our":[86,120],"knowledge,":[87],"first":[89],"fine-tuned":[91],"with":[92,106,167],"sourced":[94],"against":[101],"baseline":[103,135],"trained":[105],"established":[107],"from":[109],"developer.":[112],"Our":[113],"quantitative":[114],"evaluations":[115],"several":[117],"benefits":[118],"approach:":[121],"CCAI-trained":[123,171],"shows":[125],"lower":[126],"bias":[127],"across":[128],"nine":[129],"social":[130],"dimensions":[131],"compared":[132],"model,":[136],"while":[137],"maintaining":[138],"equivalent":[139],"performance":[140],"on":[141,157],"language,":[142],"math,":[143],"helpful-harmless":[145],"evaluations.":[146],"Qualitative":[147],"comparisons":[148],"models":[151,155],"suggest":[152],"differ":[156],"basis":[159],"their":[161],"respective":[162],"constitutions,":[163],"e.g.,":[164],"when":[165],"prompted":[166],"contentious":[168],"topics,":[169],"tends":[173],"generate":[175],"responses":[176],"reframe":[178],"matter":[180],"positively":[181],"instead":[182],"refusal.":[185],"These":[186],"results":[187],"promising,":[190],"tractable":[191],"pathway":[192],"toward":[193],"publicly":[194],"informed":[195],"development":[196],"models.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-27T09:02:27.158192","created_date":"2025-10-10T00:00:00"}