[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-293821-105":59,"doc-detail-293821-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","a-survey-on-evaluation-of-large-language-models-review-and-analysis","A Survey on Evaluation of Large Language Models - review and analysis","","A Survey on Evaluation of Large Language Models presents a comprehensive review of evaluation approaches for large language models, organizing methods around three core dimensions: what to evaluate, where to evaluate, and how to evaluate. It surveys evaluation task types across natural language processing, reasoning, medical usage, ethics, education, and natural and social science settings, then examines benchmarks and evaluation methods. The survey also highlights representative success and failure cases and outlines future challenges to support more reliable model assessment.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/a-survey-on-evaluation-of-large-language-models-review-and-analysis/293821/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/a-survey-on-evaluation-of-large-language-models-review-and-analysis/293821.png","ImageObject",300,407,{"name":92,"@type":93},"Levi","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-27","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",11,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What are the three dimensions used to organize the survey on LLM evaluation?","Question",{"text":113,"@type":114},"The survey organizes evaluation methods around what to evaluate, where to evaluate, and how to evaluate, linking tasks to benchmarks and evaluation procedures.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"Which types of evaluation tasks does the survey cover?",{"text":118,"@type":114},"It covers general NLP tasks, reasoning, medical usage, ethics, education, natural and social sciences, agent applications, and other related areas.",{"name":120,"@type":111,"acceptedAnswer":121},"How does the survey address benchmarks and evaluation methods?",{"text":122,"@type":114},"It answers the “where” and “how” questions by diving into evaluation methods and benchmarks, treating them as crucial components for assessing LLM performance.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},293821,1789669049,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},7971461740909,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","A Survey on Evaluation of Large Language Models  \nYUPENG CHANG and XU WANG, School of Artificial Intelligence, Jilin University, Changchun, China JINDONG WANG, Microsoft Research Asia, Beijing, China  \nYUAN WU, School of Artificial Intelligence, Jilin University, Changchun, China LINYI YANG, Westlake University, Hangzhou, Hangzhou, China  \nKAIJIE ZHU, Institute of Automation, Chinese Academy of Sciences, Beijing, China HAO CHEN, Carnegie Mellon University, Pittsburgh, USA  \nXIAOYUAN YI, Microsoft Research Asia, Beijing, China CUNXIANG WANG, Westlake University, Hangzhou, China YIDONG WANG and WEI YE, Peking University, Beijing, China YUE ZHANG, Westlake University, Hangzhou, China  \nYI CHANG, School of Artificial Intelligence, Jilin University, Changchun, China PHILIP S. YU, University of Illinois at Chicago, Chicago, USA  \nQIANG YANG, Hong Kong University of Science and Technology, Kowloon, China XING XIE, Microsoft Research Asia, Beijing, China  \nLarge language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications. As LLMs continue to play a vital role in both research and daily use, their evaluation becomes increasingly critical, not only at the task level, but also at the society level for better understanding of their potential risks. Over the past years, significant efforts have been made to examine LLMs from various perspectives. This paper presents a comprehensive review of these evaluation methods for LLMs, focusing on three key dimensions: what to evaluate, where to evaluate, and how to evaluate. Firstly, we provide an overview from the perspective of evaluation tasks, encompassing general natural language processing tasks, reasoning, medical usage, ethics, education, natural and social sciences, agent applications, and other areas. Secondly, we answer the ‘where’ and ‘how’ questions by diving into the evaluation methods and benchmarks, which serve as crucial components in assessing the performance of LLMs. Then, we summarize the success and failure cases of LLMs in different tasks. Finally, we shed light on several future challenges that lie ahead in LLMs evaluation. Our aim is to offer invaluable insights to researchers in the realm of LLMs evaluation, thereby aiding the development of more proficient LLMs. Our key point is that  \nY. Chang and X. Wang contributed equally to this research.  \nThis work is supported in part by NSF under grant III-2106758 .  \nAuthors’ addresses: Y. Chang, X. Wang, Y. Wu (Corresponding author), and Y. Chang, School of Artificial Intelligence, Jilin  \nUniversity, 2699 Qianjin St., Changchun, China, 130012; [e-mails: ypchang_jluai@outlook.com](e-mails: ypchang_jluai@outlook.com), [xwang22@mails.jlu.edu.cn](xwang22@mails.jlu.edu.cn),  \n[yuanwu@jlu.edu.cn](yuanwu@jlu.edu.cn); J. Wang (Corresponding author), X. Yi, and X. Xie, Microsoft Research Asia, Beijing, China; e-mail: [Jindong.wang@microsoft.com](Jindong.wang@microsoft.com); L. Yang, C. Wang, and Y. Zhang, Westlake University, Hangzhou, China; K. Zhu, Institute of Automation, Chinese Academy of Sciences, Beijing, China; H. Chen, Carnegie Mellon University, Pennsylvania, USA;  \nY. Wang and W. Ye, Peking University, Beijing, China; P. S. Yu, University of Illinois at Chicago, Illinois, USA; Q. Yang, Hong Kong University of Science and Technology, Kowloon, Hong Kong, China.  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, [requires prior specific permission and/or a fee. Request permissions from](requires prior sp","cbCaiudalyjCinFW","https://ap.wps.com/l/cbCaiudalyjCinFW","pdf",1498934,45,"English","# Introduction\n# Evaluation Tasks\n## Natural Language Processing and Reasoning\n## Medical, Ethics, and Education\n# Evaluation Methods and Benchmarks\n## Where and How to Evaluate\n# Success and Failure Cases\n# Future Challenges","[{\"question\":\"What are the three dimensions used to organize the survey on LLM evaluation?\",\"answer\":\"The survey organizes evaluation methods around what to evaluate, where to evaluate, and how to evaluate, linking tasks to benchmarks and evaluation procedures.\"},{\"question\":\"Which types of evaluation tasks does the survey cover?\",\"answer\":\"It covers general NLP tasks, reasoning, medical usage, ethics, education, natural and social sciences, agent applications, and other related areas.\"},{\"question\":\"How does the survey address benchmarks and evaluation methods?\",\"answer\":\"It answers the “where” and “how” questions by diving into evaluation methods and benchmarks, treating them as crucial components for assessing LLM performance.\"}]","A Survey on Evaluation of Large Language Models - review and analysis | PDF",113]