{"id":"https://openalex.org/W4415797151","doi":"https://doi.org/10.52202/079017-2557","title":"Axioms for AI Alignment from Human Feedback","display_name":"Axioms for AI Alignment from Human Feedback","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415797151","doi":"https://doi.org/10.52202/079017-2557"},"language":"en","primary_location":{"id":"doi:10.52202/079017-2557","doi":"https://doi.org/10.52202/079017-2557","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-2557","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.14758","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114157991","display_name":"Luise Ge","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luise Ge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103186763","display_name":"Daniel Halpern","orcid":"https://orcid.org/0000-0003-3368-7235","observed_orcids":["https://orcid.org/0000-0003-3368-7235"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Halpern","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057226813","display_name":"Evi Micha","orcid":"https://orcid.org/0000-0002-7373-5898","observed_orcids":["https://orcid.org/0000-0002-7373-5898"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Evi Micha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041089506","display_name":"Ariel D. Procaccia","orcid":"https://orcid.org/0000-0002-8774-5827","observed_orcids":["https://orcid.org/0000-0002-8774-5827"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ariel Procaccia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Itai Shapira","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Itai Shapira","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038669899","display_name":"Yevgeniy Vorobeychik","orcid":"https://orcid.org/0000-0003-2471-5345","observed_orcids":["https://orcid.org/0000-0003-2471-5345"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yevgeniy Vorobeychik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056913693","display_name":"Junlin Wu","orcid":"https://orcid.org/0009-0006-1037-1827","observed_orcids":["https://orcid.org/0009-0006-1037-1827"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junlin Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":41.0583,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.99873721,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"80439","last_page":"80465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10991","display_name":"Game Theory and Voting Systems","score":0.88919997215271,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10991","display_name":"Game Theory and Voting Systems","score":0.88919997215271,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.04670000076293945,"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":0.01269999984651804,"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/ai-alignment","display_name":"AI alignment","score":0.9110000133514404},{"id":"https://openalex.org/keywords/reinforcement-learning-from-human-feedback","display_name":"reinforcement learning from human feedback","score":0.8519999980926514},{"id":"https://openalex.org/keywords/reward-function-learning","display_name":"reward function learning","score":0.8220000267028809},{"id":"https://openalex.org/keywords/preference-aggregation","display_name":"preference aggregation","score":0.9670000076293945},{"id":"https://openalex.org/keywords/social-choice-theory","display_name":"social choice","score":0.9750000238418579},{"id":"https://openalex.org/keywords/bradley-terry-luce-model","display_name":"Bradley-Terry-Luce model","score":0.9800000190734863},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"pairwise comparison","score":0.8610000014305115},{"id":"https://openalex.org/keywords/random-utility-models","display_name":"random utility models","score":0.5400000214576721}],"concepts":[{"id":"https://openalex.org/C167729594","wikidata":"https://www.wikidata.org/wiki/Q17736","display_name":"Axiom","level":2,"score":0.7501999735832214},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6456999778747559},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6007000207901001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5532000064849854},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5212000012397766},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5022000074386597},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.46149998903274536},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4246000051498413},{"id":"https://openalex.org/C189352744","wikidata":"https://www.wikidata.org/wiki/Q1971461","display_name":"Social choice theory","level":2,"score":0.4146000146865845},{"id":"https://openalex.org/C32172795","wikidata":"https://www.wikidata.org/wiki/Q4692266","display_name":"Aggregation problem","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C79416737","wikidata":"https://www.wikidata.org/wiki/Q2305519","display_name":"Social learning","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C205706631","wikidata":"https://www.wikidata.org/wiki/Q2319304","display_name":"Expected utility hypothesis","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C125773388","wikidata":"https://www.wikidata.org/wiki/Q792542","display_name":"Axiomatic system","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26930001378059387},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2540000081062317}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/079017-2557","doi":"https://doi.org/10.52202/079017-2557","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-2557","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.14758","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.14758","pdf_url":"https://arxiv.org/pdf/2405.14758","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.2405.14758","doi":"https://doi.org/10.48550/arxiv.2405.14758","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.14758","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:2405.14758","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.14758","pdf_url":"https://arxiv.org/pdf/2405.14758","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":[{"id":"https://openalex.org/G3260182487","display_name":null,"funder_award_id":"N00014-20-1-2488","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5719362638","display_name":"AF: Small: A Computational Lens on Participatory Democracy","funder_award_id":"2007080","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5940372180","display_name":"FAI: A Normative Economic Approach to Fairness in AI","funder_award_id":"2147187","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G810252993","display_name":"CAREER: Adversarial Artificial Intelligence for Social Good","funder_award_id":"1905558","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G81194128","display_name":"RI: Small: Large-Scale Game-Theoretic Reasoning with Incomplete Information","funder_award_id":"2214141","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G826810440","display_name":"AI Institute for Societal Decision Making (AI-SDM)","funder_award_id":"2229881","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415797151.pdf","grobid_xml":"https://content.openalex.org/works/W4415797151.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2973379954","https://openalex.org/W3039563104","https://openalex.org/W4388739079","https://openalex.org/W4389761023","https://openalex.org/W4390723302","https://openalex.org/W4391835636","https://openalex.org/W4392677981","https://openalex.org/W4394906159","https://openalex.org/W4395022854","https://openalex.org/W4396601201","https://openalex.org/W4396716555"],"related_works":["https://openalex.org/W4415111447","https://openalex.org/W4281963856","https://openalex.org/W4395022854","https://openalex.org/W4416624522","https://openalex.org/W4318350868","https://openalex.org/W7125923070","https://openalex.org/W4396601201","https://openalex.org/W7165621522","https://openalex.org/W4414520407","https://openalex.org/W7220950543"],"abstract_inverted_index":{"In":[0,93],"the":[1,10,50,81,111,127],"context":[2],"of":[3,20,34,41,52,113,129],"reinforcement":[4],"learning":[5,35,100],"from":[6,16,110],"human":[7],"feedback":[8],"(RLHF),":[9],"reward":[11,37,101],"function":[12,38],"is":[13,39,116],"generally":[14],"derived":[15],"maximum":[17],"likelihood":[18],"estimation":[19],"a":[21,36,121,135],"random":[22],"utility":[23],"model":[24],"based":[25],"on":[26],"pairwise":[27],"comparisons":[28],"made":[29],"by":[30],"humans.":[31],"The":[32],"problem":[33,119],"one":[40],"preference":[42],"aggregation":[43,63],"that,":[44],"we":[45,59,95,139],"argue,":[46],"largely":[47],"falls":[48],"within":[49],"scope":[51],"social":[53,114,142],"choice":[54,115],"theory.":[55],"From":[56],"this":[57],"perspective,":[58],"can":[60],"evaluate":[61],"different":[62],"methods":[64,71],"via":[65],"established":[66],"axioms,":[67],"examining":[68],"whether":[69],"these":[70],"meet":[72,90],"or":[73],"fail":[74,88],"well-known":[75],"standards.":[76],"We":[77],"demonstrate":[78],"that":[79,117,138],"both":[80],"Bradley-Terry-Luce":[82],"Model":[83],"and":[84,132],"its":[85],"broad":[86],"generalizations":[87],"to":[89,134],"basic":[91],"axioms.":[92],"response,":[94],"develop":[96],"novel":[97],"rules":[98,131],"for":[99],"functions":[102],"with":[103],"strong":[104],"axiomatic":[105],"guarantees.":[106],"A":[107],"key":[108],"innovation":[109],"standpoint":[112],"our":[118],"has":[120],"linear":[122,141],"structure,":[123],"which":[124],"greatly":[125],"restricts":[126],"space":[128],"feasible":[130],"leads":[133],"new":[136],"paradigm":[137],"call":[140],"choice.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":3}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-11-03T00:00:00"}