{"id":"https://openalex.org/W4412888095","doi":"https://doi.org/10.18653/v1/2025.findings-acl.958","title":"MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs","display_name":"MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888095","doi":"https://doi.org/10.18653/v1/2025.findings-acl.958"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.958","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.958","pdf_url":"https://aclanthology.org/2025.findings-acl.958.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: ACL 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.958.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116082870","display_name":"Kaustubh Deshpande","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaustubh Deshpande","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116082869","display_name":"Ved Sirdeshmukh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ved Sirdeshmukh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116082871","display_name":"Johannes Mols","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Johannes Baptist Mols","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013438739","display_name":"Lifeng Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lifeng Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119181334","display_name":"Ed-Yeremai Hernandez-Cardona","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ed-Yeremai Hernandez-Cardona","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Dean Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dean Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116082873","display_name":"Jeremy Kritz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeremy Kritz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116082874","display_name":"Willow E. Primack","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Willow E. Primack","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050610019","display_name":"Summer Yue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Summer Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102748139","display_name":"Chen Xing","orcid":"https://orcid.org/0000-0003-3189-0969"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Xing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87753765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"18632","last_page":"18702"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.7141000032424927,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.7141000032424927,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.7084000110626221,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10703","display_name":"Business Process Modeling and Analysis","score":0.6427000164985657,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.8283998966217041},{"id":"https://openalex.org/keywords/frontier","display_name":"Frontier","score":0.8283435106277466},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7797915935516357},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5687713623046875},{"id":"https://openalex.org/keywords/turn-taking","display_name":"Turn-taking","score":0.4635068476200104},{"id":"https://openalex.org/keywords/turn","display_name":"Turn (biochemistry)","score":0.41568413376808167},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.16638723015785217},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.15904614329338074},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.07908928394317627},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.055482953786849976}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.8283998966217041},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.8283435106277466},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7797915935516357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5687713623046875},{"id":"https://openalex.org/C2776352735","wikidata":"https://www.wikidata.org/wiki/Q2313343","display_name":"Turn-taking","level":3,"score":0.4635068476200104},{"id":"https://openalex.org/C85641259","wikidata":"https://www.wikidata.org/wiki/Q290042","display_name":"Turn (biochemistry)","level":2,"score":0.41568413376808167},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.16638723015785217},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.15904614329338074},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.07908928394317627},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.055482953786849976},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.958","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.958","pdf_url":"https://aclanthology.org/2025.findings-acl.958.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: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.958","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.958","pdf_url":"https://aclanthology.org/2025.findings-acl.958.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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888095.pdf","grobid_xml":"https://content.openalex.org/works/W4412888095.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2900127165","https://openalex.org/W320957374","https://openalex.org/W2379107843","https://openalex.org/W3120641923","https://openalex.org/W2228992124","https://openalex.org/W4410379025","https://openalex.org/W2613954729","https://openalex.org/W2909654650","https://openalex.org/W3161619631","https://openalex.org/W4242512034"],"abstract_inverted_index":{"Kaustubh":[0],"Deshpande,":[1],"Ved":[2],"Sirdeshmukh,":[3],"Johannes":[4],"Baptist":[5],"Mols,":[6],"Lifeng":[7],"Jin,":[8],"Ed-Yeremai":[9],"Hernandez-Cardona,":[10],"Dean":[11],"Lee,":[12],"Jeremy":[13],"Kritz,":[14],"Willow":[15],"E.":[16],"Primack,":[17],"Summer":[18],"Yue,":[19],"Chen":[20],"Xing.":[21],"Findings":[22],"of":[23],"the":[24],"Association":[25],"for":[26],"Computational":[27],"Linguistics:":[28],"ACL":[29],"2025.":[30,31]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
