{"id":"https://openalex.org/W4391136507","doi":"https://doi.org/10.1145/3641289","title":"A Survey on Evaluation of Large Language Models","display_name":"A Survey on Evaluation of Large Language Models","publication_year":2024,"publication_date":"2024-01-23","ids":{"openalex":"https://openalex.org/W4391136507","doi":"https://doi.org/10.1145/3641289"},"language":"en","primary_location":{"id":"doi:10.1145/3641289","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641289","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102930702","display_name":"Yupeng Chang","orcid":"https://orcid.org/0000-0001-7178-6088"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yupeng Chang","raw_affiliation_strings":["School of Artificial Intelligence, Jilin University, Changchun, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407966","display_name":"Xu Wang","orcid":"https://orcid.org/0009-0001-5904-5313"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Wang","raw_affiliation_strings":["School of Artificial Intelligence, Jilin University, Changchun, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700956","display_name":"Jindong Wang","orcid":"https://orcid.org/0000-0002-4833-0880"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jindong Wang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102024536","display_name":"Yuan Wu","orcid":"https://orcid.org/0000-0001-6289-5872"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Wu","raw_affiliation_strings":["School of Artificial Intelligence, Jilin University, Changchun, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035082722","display_name":"Linyi Yang","orcid":"https://orcid.org/0000-0003-0667-7349"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linyi Yang","raw_affiliation_strings":["Westlake University, Hangzhou, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Westlake University, Hangzhou, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103056110","display_name":"Kaijie Zhu","orcid":"https://orcid.org/0009-0002-6220-1476"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaijie Zhu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353526","display_name":"Hao Chen","orcid":"https://orcid.org/0000-0002-1960-4803"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026595284","display_name":"Xiaoyuan Yi","orcid":"https://orcid.org/0000-0003-2710-1613"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyuan Yi","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010758235","display_name":"Cunxiang Wang","orcid":"https://orcid.org/0000-0002-3023-8082"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cunxiang Wang","raw_affiliation_strings":["Westlake University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685716","display_name":"Yidong Wang","orcid":"https://orcid.org/0009-0007-9969-8259"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidong Wang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101538186","display_name":"Wei Ye","orcid":"https://orcid.org/0000-0002-9331-4716"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Ye","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333729","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0002-5214-2268"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["Westlake University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029392006","display_name":"Yi Chang","orcid":"https://orcid.org/0000-0003-2697-8093"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Chang","raw_affiliation_strings":["School of Artificial Intelligence, Jilin University, Changchun, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036357902","display_name":"Philip S. Yu","orcid":"https://orcid.org/0000-0002-3491-5968"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip S. Yu","raw_affiliation_strings":["University of Illinois at Chicago, Chicago, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago, Chicago, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636286","display_name":"Qiang Yang","orcid":"https://orcid.org/0000-0001-5059-8360"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qiang Yang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Kowloon, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Kowloon, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044651577","display_name":"Xing Xie","orcid":"https://orcid.org/0000-0002-8608-8482"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xie","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":16,"corresponding_author_ids":["https://openalex.org/A5102930702"],"corresponding_institution_ids":["https://openalex.org/I194450716"],"apc_list":null,"apc_paid":null,"fwci":759.6592,"has_fulltext":false,"cited_by_count":2268,"citation_normalized_percentile":{"value":0.99999527,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"15","issue":"3","first_page":"1","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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":0.9988999962806702,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9848999977111816,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9818000197410583,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.7392094135284424},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5229060053825378},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19640502333641052},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09097504615783691}],"concepts":[{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.7392094135284424},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5229060053825378},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19640502333641052},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09097504615783691}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3641289","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641289","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-137727","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-137727","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4320322031","display_name":"III: Medium: Collaborative Research: Self-Supervised Recommender System Learning with Application Specific Adaption","funder_award_id":"2106758","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5722720762","display_name":null,"funder_award_id":"III-2106758","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":280,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1996020380","https://openalex.org/W2000030126","https://openalex.org/W2073147434","https://openalex.org/W2073914516","https://openalex.org/W2085281262","https://openalex.org/W2108598243","https://openalex.org/W2121227244","https://openalex.org/W2129727551","https://openalex.org/W2152594618","https://openalex.org/W2293185259","https://openalex.org/W2530395818","https://openalex.org/W2618169590","https://openalex.org/W2626804490","https://openalex.org/W2799054028","https://openalex.org/W2896457183","https://openalex.org/W2912924812","https://openalex.org/W2919115771","https://openalex.org/W2923014074","https://openalex.org/W2936695845","https://openalex.org/W2943552823","https://openalex.org/W2963327228","https://openalex.org/W2963339397","https://openalex.org/W2963672599","https://openalex.org/W2973379954","https://openalex.org/W2982295985","https://openalex.org/W2982399380","https://openalex.org/W2992347006","https://openalex.org/W3023533951","https://openalex.org/W3034850762","https://openalex.org/W3047185145","https://openalex.org/W3083410900","https://openalex.org/W3087927280","https://openalex.org/W3095319910","https://openalex.org/W3100355250","https://openalex.org/W3123340107","https://openalex.org/W3126960149","https://openalex.org/W3133542152","https://openalex.org/W3134642945","https://openalex.org/W3135190223","https://openalex.org/W3135734416","https://openalex.org/W3153833878","https://openalex.org/W3161457214","https://openalex.org/W3167252906","https://openalex.org/W3172010169","https://openalex.org/W3173777717","https://openalex.org/W3174685870","https://openalex.org/W3177813494","https://openalex.org/W3195577433","https://openalex.org/W3198685994","https://openalex.org/W3201174429","https://openalex.org/W3207316473","https://openalex.org/W3208206463","https://openalex.org/W3208933101","https://openalex.org/W3211898451","https://openalex.org/W3215698779","https://openalex.org/W4214907476","https://openalex.org/W4221167110","https://openalex.org/W4224308101","https://openalex.org/W4225405251","https://openalex.org/W4226054079","https://openalex.org/W4226278401","https://openalex.org/W4226399820","https://openalex.org/W4226485558","https://openalex.org/W4229005866","https://openalex.org/W4229019162","https://openalex.org/W4239510810","https://openalex.org/W4248083651","https://openalex.org/W4281557623","https://openalex.org/W4281690148","https://openalex.org/W4282045675","https://openalex.org/W4283026156","https://openalex.org/W4283075950","https://openalex.org/W4285113702","https://openalex.org/W4285429195","https://openalex.org/W4286233477","https://openalex.org/W4286858144","https://openalex.org/W4287207977","https://openalex.org/W4287238221","https://openalex.org/W4287670949","https://openalex.org/W4287780384","https://openalex.org/W4288088047","https://openalex.org/W4292779060","https://openalex.org/W4297437104","https://openalex.org/W4303443398","https://openalex.org/W4306313004","https://openalex.org/W4307979480","https://openalex.org/W4308244910","https://openalex.org/W4308902180","https://openalex.org/W4309208603","https://openalex.org/W4313197536","https://openalex.org/W4313559133","https://openalex.org/W4313680034","https://openalex.org/W4318389352","https://openalex.org/W4318620913","https://openalex.org/W4318719209","https://openalex.org/W4318899036","https://openalex.org/W4319460874","https://openalex.org/W4319662928","https://openalex.org/W4319793302","https://openalex.org/W4320165837","https://openalex.org/W4320854883","https://openalex.org/W4321392130","https://openalex.org/W4321649710","https://openalex.org/W4322616111","https://openalex.org/W4322622443","https://openalex.org/W4322718191","https://openalex.org/W4322718246","https://openalex.org/W4323050332","https://openalex.org/W4323546563","https://openalex.org/W4323655724","https://openalex.org/W4324129637","https://openalex.org/W4327564965","https://openalex.org/W4327810286","https://openalex.org/W4327810494","https://openalex.org/W4360834569","https://openalex.org/W4360836968","https://openalex.org/W4361806395","https://openalex.org/W4361866031","https://openalex.org/W4362515116","https://openalex.org/W4362598103","https://openalex.org/W4362655544","https://openalex.org/W4362656092","https://openalex.org/W4362679046","https://openalex.org/W4362702134","https://openalex.org/W4363676214","https://openalex.org/W4364320763","https://openalex.org/W4364378939","https://openalex.org/W4365211621","https://openalex.org/W4365460657","https://openalex.org/W4365601026","https://openalex.org/W4367175507","https://openalex.org/W4367860052","https://openalex.org/W4367860087","https://openalex.org/W4368755500","https://openalex.org/W4372047097","https://openalex.org/W4375870056","https://openalex.org/W4376633008","https://openalex.org/W4376653782","https://openalex.org/W4377010143","https://openalex.org/W4377121433","https://openalex.org/W4377157938","https://openalex.org/W4377164430","https://openalex.org/W4377866047","https://openalex.org/W4377942506","https://openalex.org/W4378189609","https://openalex.org/W4378464977","https://openalex.org/W4378465161","https://openalex.org/W4378465203","https://openalex.org/W4378465262","https://openalex.org/W4378468563","https://openalex.org/W4378473699","https://openalex.org/W4378474354","https://openalex.org/W4378499172","https://openalex.org/W4378501678","https://openalex.org/W4378509270","https://openalex.org/W4378510422","https://openalex.org/W4378510497","https://openalex.org/W4378513156","https://openalex.org/W4378603221","https://openalex.org/W4378718103","https://openalex.org/W4378718229","https://openalex.org/W4378770449","https://openalex.org/W4378942418","https://openalex.org/W4379207802","https://openalex.org/W4379473327","https://openalex.org/W4379473918","https://openalex.org/W4379474412","https://openalex.org/W4379474733","https://openalex.org/W4379539660","https://openalex.org/W4379539668","https://openalex.org/W4379540146","https://openalex.org/W4379548478","https://openalex.org/W4379933518","https://openalex.org/W4379933644","https://openalex.org/W4379958452","https://openalex.org/W4379958470","https://openalex.org/W4379958543","https://openalex.org/W4380033159","https://openalex.org/W4380136141","https://openalex.org/W4380136292","https://openalex.org/W4380136478","https://openalex.org/W4380136538","https://openalex.org/W4380353816","https://openalex.org/W4380355783","https://openalex.org/W4380551306","https://openalex.org/W4380551440","https://openalex.org/W4380558379","https://openalex.org/W4380558781","https://openalex.org/W4380569699","https://openalex.org/W4380994432","https://openalex.org/W4380994495","https://openalex.org/W4381110793","https://openalex.org/W4381556776","https://openalex.org/W4381855801","https://openalex.org/W4382142077","https://openalex.org/W4382173247","https://openalex.org/W4382240547","https://openalex.org/W4383174207","https://openalex.org/W4383175664","https://openalex.org/W4383175795","https://openalex.org/W4383180608","https://openalex.org/W4383295164","https://openalex.org/W4383473944","https://openalex.org/W4383993628","https://openalex.org/W4384071683","https://openalex.org/W4384648324","https://openalex.org/W4385245566","https://openalex.org/W4385473806","https://openalex.org/W4385571547","https://openalex.org/W4385572001","https://openalex.org/W4385572754","https://openalex.org/W4385645323","https://openalex.org/W4385682098","https://openalex.org/W4385734161","https://openalex.org/W4385970120","https://openalex.org/W4386220752","https://openalex.org/W4386567020","https://openalex.org/W4386718985","https://openalex.org/W4386721614","https://openalex.org/W4386755570","https://openalex.org/W4386794522","https://openalex.org/W4386875367","https://openalex.org/W4386908092","https://openalex.org/W4386977454","https://openalex.org/W4386977707","https://openalex.org/W4386978002","https://openalex.org/W4387162877","https://openalex.org/W4388184869","https://openalex.org/W4388708748","https://openalex.org/W4389115846","https://openalex.org/W4389518686","https://openalex.org/W4389519598","https://openalex.org/W4389520065","https://openalex.org/W4389520779","https://openalex.org/W4389523832","https://openalex.org/W4389523957","https://openalex.org/W4389524308","https://openalex.org/W4390874460","https://openalex.org/W4391090624","https://openalex.org/W4392669753","https://openalex.org/W4392669872","https://openalex.org/W4393147120","https://openalex.org/W4393147146","https://openalex.org/W4401042286","https://openalex.org/W4401042580","https://openalex.org/W4401042689","https://openalex.org/W4401043132","https://openalex.org/W4402671633","https://openalex.org/W4402671800","https://openalex.org/W4402684121","https://openalex.org/W6728551298","https://openalex.org/W6739901393","https://openalex.org/W6741814560","https://openalex.org/W6761205521","https://openalex.org/W6778883912","https://openalex.org/W6781254577","https://openalex.org/W6793737154","https://openalex.org/W6794686226","https://openalex.org/W6798182279","https://openalex.org/W6800751262","https://openalex.org/W6810081322","https://openalex.org/W6811129797","https://openalex.org/W6811340617","https://openalex.org/W6838461927","https://openalex.org/W6839041712","https://openalex.org/W6839316307","https://openalex.org/W6839548382","https://openalex.org/W6846002521","https://openalex.org/W6847050642","https://openalex.org/W6849590751","https://openalex.org/W6849710474","https://openalex.org/W6850936240","https://openalex.org/W6851214015","https://openalex.org/W6851250892","https://openalex.org/W6852502634","https://openalex.org/W6852754783","https://openalex.org/W6854260779","https://openalex.org/W6855498594","https://openalex.org/W6856227841"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2368605798","https://openalex.org/W2518037665","https://openalex.org/W2348524959","https://openalex.org/W2477036161","https://openalex.org/W2368049389","https://openalex.org/W2384861574","https://openalex.org/W4294565801"],"abstract_inverted_index":{"Large":[0],"language":[1,118],"models":[2],"(LLMs)":[3],"are":[4],"gaining":[5],"increasing":[6],"popularity":[7],"in":[8,18,29,156,172,186,198],"both":[9,30],"academia":[10],"and":[11,32,99,127,132,140,149,167],"industry,":[12],"owing":[13],"to":[14,24,68,92,96,101,192,196,225],"their":[15,35,56],"unprecedented":[16],"performance":[17,159],"various":[19,72],"applications.":[20],"As":[21],"LLMs":[22,70,171,187,202],"continue":[23],"play":[25],"a":[26,77],"vital":[27],"role":[28],"research":[31],"daily":[33],"use,":[34],"evaluation":[36,82,113,147,217],"becomes":[37],"increasingly":[38],"critical,":[39],"not":[40],"only":[41],"at":[42,48],"the":[43,49,60,110,138,146,158,165,199,206,228,235],"task":[44],"level,":[45],"but":[46],"also":[47],"society":[50],"level":[51],"for":[52,84],"better":[53,226],"understanding":[54],"of":[55,80,112,160,170,201,208,230],"potential":[57],"risks.":[58],"Over":[59],"past":[61],"years,":[62],"significant":[63],"efforts":[64],"have":[65],"been":[66],"made":[67],"examine":[69],"from":[71,109],"perspectives.":[73],"This":[74],"paper":[75],"presents":[76],"comprehensive":[78],"review":[79],"these":[81],"methods":[83,148],"LLMs,":[85],"focusing":[86],"on":[87,179],"three":[88],"key":[89,213],"dimensions:":[90],"what":[91],"evaluate":[93,97,102],",":[94,98],"where":[95],"how":[100],".":[103],"Firstly,":[104],"we":[105,136,163,176],"provide":[106],"an":[107,222],"overview":[108],"perspective":[111],"tasks,":[114,120],"encompassing":[115],"general":[116],"natural":[117,126],"processing":[119],"reasoning,":[121],"medical":[122],"usage,":[123],"ethics,":[124],"education,":[125],"social":[128],"sciences,":[129],"agent":[130],"applications,":[131],"other":[133],"areas.":[134],"Secondly,":[135],"answer":[137],"\u2018where\u2019":[139],"\u2018how\u2019":[141],"questions":[142],"by":[143],"diving":[144],"into":[145],"benchmarks,":[150],"which":[151],"serve":[152],"as":[153,221],"crucial":[154],"components":[155],"assessing":[157],"LLMs.":[161,211,231],"Then,":[162],"summarize":[164],"success":[166],"failure":[168],"cases":[169],"different":[173],"tasks.":[174],"Finally,":[175],"shed":[177],"light":[178],"several":[180],"future":[181],"challenges":[182],"that":[183,216],"lie":[184],"ahead":[185],"evaluation.":[188],"Our":[189,212],"aim":[190],"is":[191,215],"offer":[193],"invaluable":[194],"insights":[195],"researchers":[197],"realm":[200],"evaluation,":[203],"thereby":[204],"aiding":[205],"development":[207,229],"more":[209],"proficient":[210],"point":[214],"should":[218],"be":[219],"treated":[220],"essential":[223],"discipline":[224],"assist":[227],"We":[232],"consistently":[233],"maintain":[234],"related":[236],"open-source":[237],"materials":[238],"at:":[239],"https://github.com/MLGroupJLU/LLM-eval-survey":[240]},"counts_by_year":[{"year":2026,"cited_by_count":272},{"year":2025,"cited_by_count":1408},{"year":2024,"cited_by_count":567},{"year":2023,"cited_by_count":21}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}