{"id":"https://openalex.org/W7140142374","doi":"https://doi.org/10.18653/v1/2026.eacl-long.169","title":"Learning Multilingual Agentic Policy to Control Sycophancy","display_name":"Learning Multilingual Agentic Policy to Control Sycophancy","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140142374","doi":"https://doi.org/10.18653/v1/2026.eacl-long.169"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.169","doi":"https://doi.org/10.18653/v1/2026.eacl-long.169","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.169","pdf_url":"https://aclanthology.org/2026.eacl-long.169.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.eacl-long.169.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062023845","display_name":"Leonardo Ranaldi","orcid":"https://orcid.org/0000-0001-8488-4146","observed_orcids":["https://orcid.org/0000-0001-8488-4146"]},"institutions":[{"id":"https://openalex.org/I116067653","display_name":"University of Rome Tor Vergata","ror":"https://ror.org/02p77k626","country_code":"IT","type":"education","lineage":["https://openalex.org/I116067653"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","IT"],"is_corresponding":false,"raw_author_name":"Leonardo Ranaldi","raw_affiliation_strings":["ILCC , School of Informatics , University of Edinburgh , United Kingdom","OMNIA Lab & University of Rome Tor Vergata , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ILCC , School of Informatics , University of Edinburgh , United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"OMNIA Lab & University of Rome Tor Vergata , Italy","institution_ids":["https://openalex.org/I116067653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020089275","display_name":"Giulia Pucci","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I116067653","display_name":"University of Rome Tor Vergata","ror":"https://ror.org/02p77k626","country_code":"IT","type":"education","lineage":["https://openalex.org/I116067653"]},{"id":"https://openalex.org/I195460627","display_name":"University of Aberdeen","ror":"https://ror.org/016476m91","country_code":"GB","type":"education","lineage":["https://openalex.org/I195460627"]}],"countries":["GB","IT"],"is_corresponding":false,"raw_author_name":"Giulia Pucci","raw_affiliation_strings":["Department of Computing Science , University of Aberdeen , United Kingdom","OMNIA Lab & University of Rome Tor Vergata , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science , University of Aberdeen , United Kingdom","institution_ids":["https://openalex.org/I195460627"]},{"raw_affiliation_string":"OMNIA Lab & University of Rome Tor Vergata , Italy","institution_ids":["https://openalex.org/I116067653"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.4205,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95310448,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3664","last_page":"3681"},"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":0.31619998812675476,"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":0.31619998812675476,"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":0.2777999937534332,"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":0.10490000247955322,"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/sycophancy","display_name":"sycophancy","score":0.9879999756813049},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8949999809265137},{"id":"https://openalex.org/keywords/policy-learning","display_name":"policy learning","score":0.5339999794960022},{"id":"https://openalex.org/keywords/meta-policy","display_name":"meta-policy","score":0.7039999961853027},{"id":"https://openalex.org/keywords/factual-accuracy","display_name":"factual accuracy","score":0.5019999742507935}],"concepts":[{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5698999762535095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4449999928474426},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.3709999918937683},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.35659998655319214},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.35010001063346863},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.34709998965263367},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3240000009536743},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C108170787","wikidata":"https://www.wikidata.org/wiki/Q3951828","display_name":"Agency (philosophy)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29159998893737793},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.28700000047683716},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.2833999991416931},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.27219998836517334},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C37228920","wikidata":"https://www.wikidata.org/wiki/Q1307600","display_name":"Experiential learning","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C109986646","wikidata":"https://www.wikidata.org/wiki/Q546113","display_name":"Public policy","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.2565000057220459},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.169","doi":"https://doi.org/10.18653/v1/2026.eacl-long.169","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.169","pdf_url":"https://aclanthology.org/2026.eacl-long.169.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/182a9749-7181-4cce-b123-e650241edac0","doi":null,"is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/182a9749-7181-4cce-b123-e650241edac0","pdf_url":"https://www.research.ed.ac.uk/files/654067529/RanaldiPucciEACL2026LearningMultilingualAgenticPolicy.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Ranaldi, L & Pucci, G 2026, Learning multilingual agentic policy to control sycophancy. in Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics. pp. 3664\u20133681, 19th Conference of the European Chapter of the Association for Computational Linguistics, Rabat, Morocco, 24/03/26. https://doi.org/10.18653/v1/2026.eacl-long.169","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.169","doi":"https://doi.org/10.18653/v1/2026.eacl-long.169","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.169","pdf_url":"https://aclanthology.org/2026.eacl-long.169.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140142374.pdf","grobid_xml":"https://content.openalex.org/works/W7140142374.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7125517166","https://openalex.org/W7138173367","https://openalex.org/W4416036313","https://openalex.org/W7204203964","https://openalex.org/W4416036025","https://openalex.org/W7148418774","https://openalex.org/W4413240600","https://openalex.org/W4414791339","https://openalex.org/W7150948673","https://openalex.org/W7168779409"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4],"highly":[5],"effective":[6],"at":[7,134],"adapting":[8,113],"to":[9,79,114,123],"users'":[10],"styles,":[11],"preferences,":[12],"and":[13,131,158],"contextual":[14],"signals-a":[15],"property":[16],"that":[17,59,102,152,165],"underlies":[18],"much":[19],"of":[20,69],"their":[21],"practical":[22],"usefulness,":[23],"but":[24],"which":[25],"can":[26],"even":[27,36],"manifest":[28],"as":[29,48,90],"sycophancy,":[30,155],"i.e.,":[31],"alignment":[32],"with":[33,97],"user-implied":[34],"beliefs":[35],"when":[37,111],"these":[38,139],"contradict":[39],"factual":[40],"accuracy":[41],"or":[42,55],"rational":[43],"reasoning.Prior":[44],"work":[45],"treats":[46],"sycophancy":[47,77,132,167],"a":[49,62,67,91,125,136],"surface-level":[50],"artefact":[51],"addressed":[52],"via":[53,120],"inferencetime":[54],"post-hoc":[56],"methods.We":[57],"argue":[58],"it":[60,153],"is":[61,118],"policy-level":[63],"failure":[64],"arising":[65],"from":[66,141],"lack":[68],"agentic":[70,85],"control":[71,121],"over":[72],"agreement":[73],"under":[74],"pressure.To":[75],"make":[76],"tractable":[78],"explicit":[80,99],"control,":[81],"we":[82],"propose":[83],"learning":[84],"policies":[86],"modelling":[87],"LLMs'":[88],"behaviour":[89],"decision-making":[92],"problem.We":[93],"equip":[94],"the":[95,115,142,145],"model":[96],"an":[98],"action":[100],"space":[101],"includes":[103],"countering":[104],"misleading":[105],"signals,":[106],"asking":[107],"for":[108],"clarification":[109],"or,":[110],"appropriate,":[112],"user.The":[116],"policy":[117],"trained":[119],"coefficients":[122],"optimise":[124],"multi-objective":[126],"reward":[127],"balancing":[128],"task":[129],"success":[130],"resistance.Crucially,":[133],"inference,":[135],"meta-policy":[137],"infers":[138],"parameters":[140],"context.We":[143],"evaluate":[144],"proposed":[146],"method":[147],"across":[148,161],"different":[149],"benchmarks,":[150],"demonstrating":[151],"reduces":[154],"improves":[156],"performance,":[157],"generalises":[159],"robustly":[160],"languages.These":[162],"findings":[163],"suggest":[164],"mitigating":[166],"requires":[168],"moving":[169],"beyond":[170],"compliance-oriented":[171],"generation":[172],"towards":[173],"agreement-agentic":[174],"control.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-25T09:29:13.331239","created_date":"2026-03-24T00:00:00"}