{"id":"https://openalex.org/W4415230966","doi":"https://doi.org/10.1609/aies.v8i1.36598","title":"SycEval: Evaluating LLM Sycophancy","display_name":"SycEval: Evaluating LLM Sycophancy","publication_year":2025,"publication_date":"2025-10-15","ids":{"openalex":"https://openalex.org/W4415230966","doi":"https://doi.org/10.1609/aies.v8i1.36598"},"language":"en","primary_location":{"id":"doi:10.1609/aies.v8i1.36598","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aies.v8i1.36598","pdf_url":"https://ojs.aaai.org/index.php/AIES/article/download/36598/38736","source":{"id":"https://openalex.org/S5407048695","display_name":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","issn_l":"3065-8365","issn":["3065-8365"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ojs.aaai.org/index.php/AIES/article/download/36598/38736","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104773752","display_name":"Aaron Fanous","orcid":"https://orcid.org/0009-0001-4404-4828"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron Fanous","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jacob Goldberg","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Goldberg","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086791197","display_name":"Ank A Agarwal","orcid":"https://orcid.org/0000-0002-8307-4931"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ank Agarwal","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Joanna Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joanna Lin","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Anson Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anson Zhou","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113182664","display_name":"Sonnet Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sonnet Xu","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084488156","display_name":"Vasiliki Bikia","orcid":"https://orcid.org/0000-0002-4660-1560"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vasiliki Bikia","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014300312","display_name":"Roxana Daneshjou","orcid":"https://orcid.org/0000-0001-7988-9356"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roxana Daneshjou","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5116269217","display_name":"Sanmi Koyejo","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanmi Koyejo","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":50.1904,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.99926523,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"8","issue":"1","first_page":"893","last_page":"900"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.38449999690055847,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.38449999690055847,"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/safer","display_name":"SAFER","score":0.7293000221252441},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6351000070571899},{"id":"https://openalex.org/keywords/persistence","display_name":"Persistence (discontinuity)","score":0.3458999991416931},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.28299999237060547}],"concepts":[{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.7293000221252441},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6351000070571899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.399399995803833},{"id":"https://openalex.org/C2781009140","wikidata":"https://www.wikidata.org/wiki/Q7170389","display_name":"Persistence (discontinuity)","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3384000062942505},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.295199990272522},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C2779329348","wikidata":"https://www.wikidata.org/wiki/Q1400937","display_name":"Feedlot","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.23330000042915344},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.23240000009536743}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aies.v8i1.36598","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aies.v8i1.36598","pdf_url":"https://ojs.aaai.org/index.php/AIES/article/download/36598/38736","source":{"id":"https://openalex.org/S5407048695","display_name":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","issn_l":"3065-8365","issn":["3065-8365"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/36598","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AIES/article/view/36598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"3065-8365","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aies.v8i1.36598","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aies.v8i1.36598","pdf_url":"https://ojs.aaai.org/index.php/AIES/article/download/36598/38736","source":{"id":"https://openalex.org/S5407048695","display_name":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","issn_l":"3065-8365","issn":["3065-8365"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415230966.pdf","grobid_xml":"https://content.openalex.org/works/W4415230966.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"applied":[6],"in":[7,35,52,75,88,110,175],"educational,":[8],"clinical,":[9],"and":[10,38,43,63,170,177,185],"professional":[11],"settings,":[12],"but":[13],"their":[14],"tendency":[15],"for":[16,188],"sycophancy\u2014prioritizing":[17],"user":[18],"agreement":[19],"over":[20],"independent":[21],"reasoning\u2014poses":[22],"risks":[23,169],"to":[24,31,71,83],"reliability.":[25],"This":[26],"study":[27],"introduces":[28],"a":[29],"framework":[30],"evaluate":[32],"sycophantic":[33],"behavior":[34,49,151],"ChatGPT-4o,":[36],"Claude-Sonnet,":[37],"Gemini-1.5-Pro":[39],"across":[40],"AMPS":[41],"(mathematics)":[42],"MedQuad":[44],"(medical":[45],"advice)":[46],"datasets.":[47],"Sycophantic":[48,150],"was":[50,86],"observed":[51,87],"58.19%":[53],"of":[54,77,161,172],"cases,":[55,78],"with":[56],"Gemini":[57],"exhibiting":[58],"the":[59,65,140,168],"highest":[60,141],"rate":[61],"(62.47%)":[62],"ChatGPT":[64],"lowest":[66],"(56.71%).":[67],"Progressive":[68],"sycophancy,":[69,81],"leading":[70,82],"correct":[72],"answers,":[73,85],"occurred":[74],"43.52%":[76],"while":[79,136],"regressive":[80,114,142],"incorrect":[84],"14.66%.":[89],"Preemptive":[90],"rebuttals":[91,99,126,138],"demonstrated":[92],"significantly":[93,117],"higher":[94],"sycophancy":[95,115,129],"rates":[96,143],"than":[97],"in-context":[98],"(61.75%":[100],"vs.":[101],"56.52%,":[102],"Z":[103],"=":[104,131,145],"5.87,":[105],"p":[106,122,133,147],"<":[107,123,134,148],"0.001),":[108,135],"particularly":[109],"computational":[111],"tasks,":[112],"where":[113],"increased":[116],"(preemptive:":[118],"8.13%,":[119],"in-context:":[120],"3.54%,":[121],"0.001).":[124,149],"Simple":[125],"maximized":[127],"progressive":[128],"(Z":[130,144],"6.59,":[132,146],"citation-based":[137],"exhibited":[139],"showed":[152],"high":[153],"persistence":[154],"(78.5%,":[155],"95%":[156],"CI:":[157],"[77.2%,":[158],"79.8%])":[159],"regardless":[160],"context":[162],"or":[163],"model.":[164],"These":[165],"findings":[166],"emphasize":[167],"opportunities":[171],"deploying":[173],"LLMs":[174],"structured":[176],"dynamic":[178],"domains,":[179],"offering":[180],"insights":[181],"into":[182],"prompt":[183],"programming":[184],"model":[186],"optimization":[187],"safer":[189],"AI":[190],"applications":[191]},"counts_by_year":[{"year":2026,"cited_by_count":26},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-16T00:00:00"}