{"id":"https://openalex.org/W4416036025","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.121","title":"Measuring Sycophancy of Language Models in Multi-turn Dialogues","display_name":"Measuring Sycophancy of Language Models in Multi-turn Dialogues","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036025","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.121"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.121","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.121","pdf_url":"https://aclanthology.org/2025.findings-emnlp.121.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.121.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104265270","display_name":"Jiseung Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiseung Hong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120308978","display_name":"Grace Byun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grace Byun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014381991","display_name":"Seungone Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seungone Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5058670321","display_name":"Kai Shu","orcid":"https://orcid.org/0000-0002-6043-1764"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Shu","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":15.0571,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.99213487,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2239","last_page":"2259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.23420000076293945,"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/T12031","display_name":"Speech and dialogue systems","score":0.23420000076293945,"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/T10028","display_name":"Topic Modeling","score":0.16990000009536743,"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/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.15530000627040863,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6948999762535095},{"id":"https://openalex.org/keywords/exposition","display_name":"Exposition (narrative)","score":0.6780999898910522},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.664900004863739},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5558000206947327},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3702000081539154},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.3174999952316284}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6948999762535095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6837000250816345},{"id":"https://openalex.org/C2776285698","wikidata":"https://www.wikidata.org/wiki/Q2642214","display_name":"Exposition (narrative)","level":2,"score":0.6780999898910522},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.664900004863739},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5558000206947327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4787999987602234},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3702000081539154},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3416999876499176},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.305400013923645},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2939000129699707},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29109999537467957},{"id":"https://openalex.org/C543847140","wikidata":"https://www.wikidata.org/wiki/Q2642826","display_name":"Realism","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2678000032901764}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.121","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.121","pdf_url":"https://aclanthology.org/2025.findings-emnlp.121.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.23840","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.23840","pdf_url":"https://arxiv.org/pdf/2505.23840","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"pmh:doi:10.48550/arxiv.2505.23840","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.121","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.121","pdf_url":"https://aclanthology.org/2025.findings-emnlp.121.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7721754942","display_name":"CAREER: Towards Fairness in the Real World under Generalization, Privacy and Robustness Challenges","funder_award_id":"2506643","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036025.pdf","grobid_xml":"https://content.openalex.org/works/W4416036025.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4],"expected":[5],"to":[6,17,68,90,124,168],"provide":[7],"helpful":[8],"and":[9,74,117,157,176],"harmless":[10],"responses,":[11],"yet":[12],"they":[13,138],"often":[14,135],"exhibit":[15],"sycophancy-conforming":[16],"user":[18,70,83,127],"beliefs":[19],"regardless":[20],"of":[21,40,72,86,144],"factual":[22,35],"accuracy":[23],"or":[24],"ethical":[25],"soundness.Prior":[26],"research":[27],"on":[28,33,140],"sycophancy":[29,100,165],"has":[30],"primarily":[31],"focused":[32],"single-turn":[34],"correctness,":[36],"overlooking":[37],"the":[38,69,121,147],"dynamics":[39],"real-world":[41,95],"interactions.In":[42],"this":[43],"work,":[44],"we":[45,97,151],"introduce":[46],"SYCON":[47,88],"BENCH,":[48],"a":[49,65,102,161],"novel":[50],"benchmark":[51,61],"for":[52],"evaluating":[53],"sycophantic":[54,112],"behavior":[55],"in":[56,170],"multiturn,":[57],"free-form":[58],"conversational":[59],"settings.Our":[60],"measures":[62],"how":[63,75],"quickly":[64],"model":[66,115],"conforms":[67],"(Turn":[71],"Flip)":[73],"frequently":[76],"it":[77],"shifts":[78],"its":[79],"stance":[80],"under":[81],"sustained":[82],"pressure":[84],"(Number":[85],"Flip).Applying":[87],"BENCH":[89],"17":[91],"LLMs":[92],"across":[93],"three":[94],"scenarios,":[96],"find":[98],"that":[99,108,159],"remains":[101],"prevalent":[103],"failure":[104],"mode.Our":[105],"analysis":[106],"shows":[107],"alignment":[109],"tuning":[110],"amplifies":[111],"behavior,":[113],"whereas":[114],"scaling":[116],"reasoning":[118],"optimization":[119],"strengthen":[120],"model's":[122],"ability":[123],"resist":[125],"undesirable":[126],"views.Reasoning":[128],"models":[129,133],"generally":[130],"outperform":[131],"instruction-tuned":[132],"but":[134],"fail":[136],"when":[137],"over-index":[139],"logical":[141],"exposition":[142],"instead":[143],"directly":[145],"addressing":[146],"user's":[148],"underlying":[149],"beliefs.Finally,":[150],"evaluate":[152],"four":[153],"additional":[154],"prompting":[155],"strategies":[156],"demonstrate":[158],"adopting":[160],"third-person":[162],"perspective":[163],"reduces":[164],"by":[166],"up":[167],"63.8%":[169],"debate":[171],"scenario.We":[172],"release":[173],"our":[174],"code":[175],"data":[177],"at":[178],"https:":[179],"//github.com/JiseungHong/SYCON-Bench.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}