{"id":"https://openalex.org/W7166805633","doi":"https://doi.org/10.18653/v1/2026.acl-long.972","title":"LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models","display_name":"LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166805633","doi":"https://doi.org/10.18653/v1/2026.acl-long.972"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.972","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.972","pdf_url":"https://aclanthology.org/2026.acl-long.972.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.972.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139758323","display_name":"Ming Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139792994","display_name":"Yujiong Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujiong Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139744102","display_name":"Jingyi Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingyi Deng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139792583","display_name":"Yuhui Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhui Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122296278","display_name":"Huayu Sha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huayu Sha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136510983","display_name":"Kexin Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kexin Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126104217","display_name":"Qiyuan Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiyuan Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139734299","display_name":"Yue Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139796734","display_name":"Junzhe Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junzhe Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139850163","display_name":"Shichun Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shichun Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139760057","display_name":"Yueyuan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yueyuan Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113207942","display_name":"Jingqi Tong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingqi Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139736396","display_name":"Changhao Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changhao Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100864237","display_name":"Yilong Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yilong Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139744205","display_name":"Zhihao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhihao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123485941","display_name":"Mingqi Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingqi Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109693861","display_name":"Mingxu Chai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingxu Chai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139764928","display_name":"Zhiheng Xi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiheng Xi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139758494","display_name":"Shihan Dou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shihan Dou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139809977","display_name":"Tao Gui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Gui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139758763","display_name":"Qi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139829847","display_name":"Xuanjing Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuanjing Huang","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":0.84265734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21246","last_page":"21273"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.4156999886035919,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.4156999886035919,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.11460000276565552,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.05310000106692314,"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/computational-linguistics","display_name":"Computational linguistics","score":0.4334999918937683},{"id":"https://openalex.org/keywords/longitudinal-study","display_name":"Longitudinal study","score":0.4268999993801117},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.33570000529289246},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3165999948978424},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.30559998750686646},{"id":"https://openalex.org/keywords/longitudinal-data","display_name":"Longitudinal data","score":0.2930000126361847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5554999709129333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43709999322891235},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.4334999918937683},{"id":"https://openalex.org/C2777895361","wikidata":"https://www.wikidata.org/wiki/Q1758614","display_name":"Longitudinal study","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.39959999918937683},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38839998841285706},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C3020672099","wikidata":"https://www.wikidata.org/wiki/Q857354","display_name":"Longitudinal data","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27730000019073486},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2651999890804291}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.972","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.972","pdf_url":"https://aclanthology.org/2026.acl-long.972.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.972","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.972","pdf_url":"https://aclanthology.org/2026.acl-long.972.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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8574973940849304}],"awards":[{"id":"https://openalex.org/G1187148928","display_name":null,"funder_award_id":"62376061","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5542150374","display_name":null,"funder_award_id":"62476061","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166805633.pdf","grobid_xml":"https://content.openalex.org/works/W7166805633.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Ming":[0],"Zhang,":[1,15,29,41],"Yujiong":[2],"Shen,":[3],"Jingyi":[4],"Deng,":[5],"Yuhui":[6],"Wang,":[7,17],"Huayu":[8],"Sha,":[9],"Kexin":[10],"Tan,":[11],"Qiyuan":[12],"Peng,":[13],"Yue":[14],"Junzhe":[16],"Shichun":[18],"Liu,":[19],"Yueyuan":[20],"Huang,":[21],"Jingqi":[22],"Tong,":[23],"Changhao":[24],"Jiang,":[25],"Yilong":[26],"Wu,":[27,31],"Zhihao":[28],"Mingqi":[30],"Mingxu":[32],"Chai,":[33],"Zhiheng":[34],"Xi,":[35],"Shihan":[36],"Dou,":[37],"Tao":[38],"Gui,":[39],"Qi":[40],"Xuanjing":[42],"Huang.":[43],"Proceedings":[44],"of":[45,50],"the":[46,51],"64th":[47],"Annual":[48],"Meeting":[49],"Association":[52],"for":[53],"Computational":[54],"Linguistics":[55],"(Volume":[56],"1:":[57],"Long":[58],"Papers).":[59],"2026.":[60]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}