{"id":"https://openalex.org/W7166876594","doi":"https://doi.org/10.18653/v1/2026.acl-long.2192","title":"Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations","display_name":"Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166876594","doi":"https://doi.org/10.18653/v1/2026.acl-long.2192"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.2192","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2192","pdf_url":"https://aclanthology.org/2026.acl-long.2192.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.2192.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139727127","display_name":"Preethi Seshadri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Preethi Seshadri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139827000","display_name":"Samuel Cahyawijaya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Cahyawijaya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139834741","display_name":"Ayomide Odumakinde","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ayomide Odumakinde","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139743915","display_name":"Sameer Singh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sameer Singh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139769899","display_name":"Seraphina Goldfarb-Tarrant","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seraphina Goldfarb-Tarrant","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":0.86471965,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"47423","last_page":"47439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.1379999965429306,"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":0.1379999965429306,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.09830000251531601,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.06440000236034393,"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":0.38029998540878296},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.272599995136261},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.2669000029563904},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.25519999861717224}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.47679999470710754},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44830000400543213},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3513999879360199},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.2924000024795532},{"id":"https://openalex.org/C75630572","wikidata":"https://www.wikidata.org/wiki/Q538904","display_name":"Applied psychology","level":1,"score":0.28760001063346863},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2727000117301941},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.2192","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2192","pdf_url":"https://aclanthology.org/2026.acl-long.2192.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.2192","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2192","pdf_url":"https://aclanthology.org/2026.acl-long.2192.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":[{"display_name":"Quality Education","score":0.8833009004592896,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6416336507","display_name":"CAREER: Detecting, Understanding, and Fixing Vulnerabilities in Natural Language Processing Models","funder_award_id":"2046873","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","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/W7166876594.pdf","grobid_xml":"https://content.openalex.org/works/W7166876594.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Preethi":[0],"Seshadri,":[1],"Samuel":[2],"Cahyawijaya,":[3],"Ayomide":[4],"Odumakinde,":[5],"Sameer":[6],"Singh,":[7],"Seraphina":[8],"Goldfarb-Tarrant.":[9],"Proceedings":[10],"of":[11,16],"the":[12,17],"64th":[13],"Annual":[14],"Meeting":[15],"Association":[18],"for":[19],"Computational":[20],"Linguistics":[21],"(Volume":[22],"1:":[23],"Long":[24],"Papers).":[25],"2026.":[26]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}