{"id":"https://openalex.org/W4414930097","doi":"https://doi.org/10.18653/v1/2026.acl-long.922","title":"League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models","display_name":"League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414930097","doi":"https://doi.org/10.18653/v1/2026.acl-long.922"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.922","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.922","pdf_url":"https://aclanthology.org/2026.acl-long.922.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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.922.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038564224","display_name":"Q. H. Guo","orcid":"https://orcid.org/0009-0000-0898-1489"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qianhong Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100617970","display_name":"W. Xie","orcid":"https://orcid.org/0000-0003-1430-9191"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110675067","display_name":"Xiaofang Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaofang Cai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100761561","display_name":"Enze Wang","orcid":"https://orcid.org/0000-0003-2521-063X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Enze Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059973732","display_name":"Sisi Ma","orcid":"https://orcid.org/0000-0003-2956-6844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuoyoucheng Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaobing Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaobing Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Tian Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Xia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101972333","display_name":"Kai Chen","orcid":"https://orcid.org/0009-0007-4458-7367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333210","display_name":"Xiaofeng Wang","orcid":"https://orcid.org/0000-0001-6259-7971"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaofeng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100612192","display_name":"Baosheng Wang","orcid":"https://orcid.org/0000-0001-6187-0294"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baosheng Wang","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":0.01041994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20138","last_page":"20159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9656000137329102,"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":0.9656000137329102,"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":0.9487000107765198,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.6439999938011169},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.6037999987602234},{"id":"https://openalex.org/keywords/league","display_name":"League","score":0.5968999862670898},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4950999915599823},{"id":"https://openalex.org/keywords/mainstream","display_name":"Mainstream","score":0.46140000224113464},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.413100004196167},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.39879998564720154},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.3711000084877014}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6439999938011169},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.6037999987602234},{"id":"https://openalex.org/C207456731","wikidata":"https://www.wikidata.org/wiki/Q660818","display_name":"League","level":2,"score":0.5968999862670898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5324000120162964},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.46140000224113464},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40220001339912415},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3345000147819519},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33250001072883606},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3149999976158142},{"id":"https://openalex.org/C168725872","wikidata":"https://www.wikidata.org/wiki/Q991663","display_name":"Sophistication","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.311599999666214},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.3109000027179718},{"id":"https://openalex.org/C2779812341","wikidata":"https://www.wikidata.org/wiki/Q5891525","display_name":"Homophily","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C3020552257","wikidata":"https://www.wikidata.org/wiki/Q6509135","display_name":"League table","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2892000079154968},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2630999982357025},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C137403100","wikidata":"https://www.wikidata.org/wiki/Q41710","display_name":"Ethnic group","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.922","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.922","pdf_url":"https://aclanthology.org/2026.acl-long.922.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"},{"id":"pmh:oai:arXiv.org:2507.22359","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2507.22359","pdf_url":"https://arxiv.org/pdf/2507.22359","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"doi:10.48550/arxiv.2507.22359","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.22359","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.922","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.922","pdf_url":"https://aclanthology.org/2026.acl-long.922.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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414930097.pdf","grobid_xml":"https://content.openalex.org/works/W4414930097.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Qianhong":[0],"Guo,":[1],"Wei":[2],"Xie,":[3],"Xiaofang":[4],"Cai,":[5],"Enze":[6],"Wang,":[7,17],"Shuoyoucheng":[8],"Ma,":[9],"Xiaobing":[10],"Sun,":[11],"Tian":[12],"Xia,":[13],"Kai":[14],"Chen,":[15],"Xiaofeng":[16],"Baosheng":[18],"Wang.":[19],"Proceedings":[20],"of":[21,26],"the":[22,27],"64th":[23],"Annual":[24],"Meeting":[25],"Association":[28],"for":[29],"Computational":[30],"Linguistics":[31],"(Volume":[32],"1:":[33],"Long":[34],"Papers).":[35],"2026.":[36]},"counts_by_year":[],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}