{"id":"https://openalex.org/W7166807399","doi":"https://doi.org/10.18653/v1/2026.acl-long.1770","title":"Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs","display_name":"Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166807399","doi":"https://doi.org/10.18653/v1/2026.acl-long.1770"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1770","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1770","pdf_url":"https://aclanthology.org/2026.acl-long.1770.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1770.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139678638","display_name":"Nikita Afonin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikita Afonin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137675720","display_name":"Nikita Andriianov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikita Andriianov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111085168","display_name":"Vahagn Hovhannisyan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vahagn Hovhannisyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139786680","display_name":"Nikhil Bageshpura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikhil Bageshpura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104229507","display_name":"Kyle Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyle Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139758621","display_name":"Kevin Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139778930","display_name":"Sunishchal Dev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sunishchal Dev","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139770716","display_name":"Ashwinee Panda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashwinee Panda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139746298","display_name":"Oleg Rogov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oleg Rogov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139821565","display_name":"Elena Tutubalina","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elena Tutubalina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139810548","display_name":"Alexander Panchenko","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Panchenko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139803200","display_name":"Mikhail Seleznyov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikhail Seleznyov","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79729227,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"38197","last_page":"38212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4869000017642975,"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/T10028","display_name":"Topic Modeling","score":0.4869000017642975,"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":0.13750000298023224,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.040699999779462814,"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/association","display_name":"Association (psychology)","score":0.28299999237060547}],"concepts":[{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.3921999931335449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3889999985694885},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.349700003862381},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.3231000006198883},{"id":"https://openalex.org/C29595303","wikidata":"https://www.wikidata.org/wiki/Q165650","display_name":"Media studies","level":1,"score":0.28999999165534973},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2660999894142151},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.258899986743927},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.25369998812675476},{"id":"https://openalex.org/C178802073","wikidata":"https://www.wikidata.org/wiki/Q8421","display_name":"Aeronautics","level":1,"score":0.21930000185966492}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1770","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1770","pdf_url":"https://aclanthology.org/2026.acl-long.1770.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1770","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1770","pdf_url":"https://aclanthology.org/2026.acl-long.1770.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6532952785491943,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1061213447","display_name":null,"funder_award_id":"139-15-2025-011","funder_id":"https://openalex.org/F4320334801","funder_display_name":"Russian Academy of Sciences"},{"id":"https://openalex.org/G8222445775","display_name":null,"funder_award_id":"139-15-2025-011","funder_id":"https://openalex.org/F4320324632","funder_display_name":"Ministero dello Sviluppo Economico"}],"funders":[{"id":"https://openalex.org/F4320324632","display_name":"Ministero dello Sviluppo Economico","ror":"https://ror.org/011z3ff80"},{"id":"https://openalex.org/F4320334801","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166807399.pdf","grobid_xml":"https://content.openalex.org/works/W7166807399.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Nikita":[0,2],"Afonin,":[1],"Andriianov,":[3],"Vahagn":[4],"Hovhannisyan,":[5],"Nikhil":[6],"Bageshpura,":[7],"Kyle":[8],"Liu,":[9],"Kevin":[10],"Zhu,":[11],"Sunishchal":[12],"Dev,":[13],"Ashwinee":[14],"Panda,":[15],"Oleg":[16],"Rogov,":[17],"Elena":[18],"Tutubalina,":[19],"Alexander":[20],"Panchenko,":[21],"Mikhail":[22],"Seleznyov.":[23],"Proceedings":[24],"of":[25,30],"the":[26,31],"64th":[27],"Annual":[28],"Meeting":[29],"Association":[32],"for":[33],"Computational":[34],"Linguistics":[35],"(Volume":[36],"1:":[37],"Long":[38],"Papers).":[39],"2026.":[40]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
