{"id":"https://openalex.org/W3148330722","doi":"https://doi.org/10.48550/arxiv.2103.14659","title":"Alignment of Language Agents","display_name":"Alignment of Language Agents","publication_year":2021,"publication_date":"2021-03-26","ids":{"openalex":"https://openalex.org/W3148330722","doi":"https://doi.org/10.48550/arxiv.2103.14659","mag":"3148330722"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2103.14659","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.14659","pdf_url":"https://arxiv.org/pdf/2103.14659","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.14659","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069438696","display_name":"Zachary Kenton","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenton, Zachary","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020224050","display_name":"Tom Everitt","orcid":"https://orcid.org/0000-0003-1210-9866","observed_orcids":["https://orcid.org/0000-0003-1210-9866"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Everitt, Tom","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056575786","display_name":"Laura Weidinger","orcid":"https://orcid.org/0000-0002-5189-760X","observed_orcids":["https://orcid.org/0000-0002-5189-760X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weidinger, Laura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032814084","display_name":"Iason Gabriel","orcid":"https://orcid.org/0000-0002-7552-4576","observed_orcids":["https://orcid.org/0000-0002-7552-4576"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabriel, Iason","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047554131","display_name":"Vladimir Mikulik","orcid":"https://orcid.org/0000-0002-0452-6785","observed_orcids":["https://orcid.org/0000-0002-0452-6785"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikulik, Vladimir","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5029611587","display_name":"Geoffrey Irving","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Irving, Geoffrey","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":null,"has_fulltext":false,"cited_by_count":45,"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":0.8163999915122986,"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":0.8163999915122986,"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/T12031","display_name":"Speech and dialogue systems","score":0.06159999966621399,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0430000014603138,"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/language-agents","display_name":"language agents","score":0.8790000081062317},{"id":"https://openalex.org/keywords/ai-alignment","display_name":"AI alignment","score":0.9110000133514404},{"id":"https://openalex.org/keywords/model-misspecification","display_name":"model misspecification","score":0.746999979019165},{"id":"https://openalex.org/keywords/linguistic-manipulation","display_name":"language manipulation","score":0.9539999961853027},{"id":"https://openalex.org/keywords/agent-behavior","display_name":"agent behavior","score":0.5889999866485596},{"id":"https://openalex.org/keywords/human-ai-interaction","display_name":"human-AI interaction","score":0.6589999794960022}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6140073537826538},{"id":"https://openalex.org/C126965237","wikidata":"https://www.wikidata.org/wiki/Q816335","display_name":"Accidental","level":2,"score":0.45393574237823486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4506228566169739},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.4316129684448242},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.29327183961868286},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2103.14659","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.14659","pdf_url":"https://arxiv.org/pdf/2103.14659","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.2103.14659","doi":"https://doi.org/10.48550/arxiv.2103.14659","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.14659","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:2103.14659","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.14659","pdf_url":"https://arxiv.org/pdf/2103.14659","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":[],"sustainable_development_goals_aurora":[{"score":0.6499999761581421,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W42806799","https://openalex.org/W140903904","https://openalex.org/W648152870","https://openalex.org/W1714490037","https://openalex.org/W1934909785","https://openalex.org/W2018528947","https://openalex.org/W2040849715","https://openalex.org/W2041607960","https://openalex.org/W2083898265","https://openalex.org/W2088731121","https://openalex.org/W2089192547","https://openalex.org/W2129286663","https://openalex.org/W2161466446","https://openalex.org/W2163833659","https://openalex.org/W2174179791","https://openalex.org/W2462906003","https://openalex.org/W2472097883","https://openalex.org/W2488194301","https://openalex.org/W2504696229","https://openalex.org/W2525639264","https://openalex.org/W2526781987","https://openalex.org/W2558801266","https://openalex.org/W2574075983","https://openalex.org/W2603790972","https://openalex.org/W2625113742","https://openalex.org/W2768908787","https://openalex.org/W2770550542","https://openalex.org/W2787887017","https://openalex.org/W2798877128","https://openalex.org/W2799058376","https://openalex.org/W2804621770","https://openalex.org/W2896930824","https://openalex.org/W2901707424","https://openalex.org/W2904670791","https://openalex.org/W2906152891","https://openalex.org/W2917705988","https://openalex.org/W2917742641","https://openalex.org/W2948625193","https://openalex.org/W2958608582","https://openalex.org/W2962787423","https://openalex.org/W2962943921","https://openalex.org/W2963646405","https://openalex.org/W2968771440","https://openalex.org/W2970583189","https://openalex.org/W2971171756","https://openalex.org/W2971307358","https://openalex.org/W2973907375","https://openalex.org/W2981852735","https://openalex.org/W2983486364","https://openalex.org/W3002093512","https://openalex.org/W3017311573","https://openalex.org/W3019416653","https://openalex.org/W3030163527","https://openalex.org/W3034344071","https://openalex.org/W3088599783","https://openalex.org/W3090395639","https://openalex.org/W3092918135","https://openalex.org/W3098985263","https://openalex.org/W3100511085","https://openalex.org/W3128232076","https://openalex.org/W3128912454","https://openalex.org/W3133702157","https://openalex.org/W3173549437","https://openalex.org/W3175333484","https://openalex.org/W3193991359","https://openalex.org/W3209859203"],"related_works":["https://openalex.org/W4386001197","https://openalex.org/W4393156488","https://openalex.org/W4283834526","https://openalex.org/W4401657904","https://openalex.org/W7131078810","https://openalex.org/W2142585188","https://openalex.org/W7054953981","https://openalex.org/W4416074906","https://openalex.org/W4366390744","https://openalex.org/W7152107576"],"abstract_inverted_index":{"For":[0],"artificial":[1],"intelligence":[2],"to":[3,6,14],"be":[4,15],"beneficial":[5],"humans":[7,19],"the":[8,37],"behaviour":[9],"of":[10],"AI":[11],"agents":[12],"needs":[13],"aligned":[16],"with":[17],"what":[18],"want.":[20],"In":[21],"this":[22],"paper":[23],"we":[24],"discuss":[25,49],"some":[26,42,50,65],"behavioural":[27,51],"issues":[28,52],"for":[29,67],"language":[30],"agents,":[31],"arising":[32],"from":[33,56],"accidental":[34],"misspecification":[35,45],"by":[36],"system":[38],"designer.":[39],"We":[40],"highlight":[41],"ways":[43],"that":[44,53],"can":[46],"occur":[47],"and":[48,63],"could":[54],"arise":[55],"misspecification,":[57],"including":[58],"deceptive":[59],"or":[60],"manipulative":[61],"language,":[62],"review":[64],"approaches":[66],"avoiding":[68],"these":[69],"issues.":[70]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-04-13T00:00:00"}