[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-293791-105":59,"doc-detail-293791-en":130},{"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":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","a-survey-on-evaluation-of-large-language-models-a-survey-on-evaluation","A Survey on Evaluation of Large Language Models - A Survey on Evaluation","","A Survey on Evaluation of Large Language Models presents a comprehensive review of how large language models (LLMs) are evaluated across academia and industry. It organizes evaluation along three dimensions: what to evaluate, where to evaluate (methods and benchmarks), and how to evaluate. The survey covers evaluation tasks spanning NLP, reasoning, medical usage, ethics, education, natural and social sciences, and agent applications, and it summarizes representative success and failure cases while discussing future challenges and open resources.",{"@graph":69,"@context":122},[70,84,105],{"@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-a-survey-on-evaluation/293791/",{"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-a-survey-on-evaluation/293791.png","ImageObject",300,407,{"name":92,"@type":93},"Blitz","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-08","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What are the three key dimensions used to structure LLM evaluation in the survey?","Question",{"text":112,"@type":113},"The survey organizes evaluation into three dimensions: what to evaluate, where to evaluate (methods and benchmarks), and how to evaluate.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Which kinds of evaluation tasks does the survey cover?",{"text":117,"@type":113},"It covers general NLP tasks, reasoning, medical usage, ethics, education, natural and social sciences, agent applications, and other related areas.",{"name":119,"@type":110,"acceptedAnswer":120},"How does the survey treat “where” and “how” evaluation questions?",{"text":121,"@type":113},"It addresses them by diving into evaluation methods and benchmarks, which are described as crucial components for assessing LLM performance.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},293791,1789668885,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":52,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":144,"preview_page_count":4},24464137899374,"https://us-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","arXiv :2307 .03109v9 [ cs .CL] 29 Dec 2023  \nA Survey on Evaluation of Large Language Models  \nYUPENG CHANG∗ and XU WANG∗ , School of Artificial Intelligence, Jilin University, China JINDONG WANG†, Microsoft Research Asia, China  \nYUAN WU†, School of Artificial Intelligence, Jilin University, China LINYI YANG, Westlake University, China  \nKAIJIE ZHU, Institute of Automation, Chinese Academy of Sciences, China HAO CHEN, Carnegie Mellon University, USA  \nXIAOYUAN YI, Microsoft Research Asia, China CUNXIANG WANG, Westlake University, China YIDONG WANG, Peking University, China WEI YE, Peking University, China  \nYUE ZHANG, Westlake University, China  \nYI CHANG, School of Artificial Intelligence, Jilin University, China PHILIP S. YU, University of Illinois at Chicago, USA  \nQIANG YANG, Hong Kong University of Science and Technology, China XING XIE, Microsoft Research Asia, 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 atthe 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  \n∗ Both authors contributed equally to this research.†Corresponding author.  \nAuthors’ addresses: Yupeng Chang, [ypchang_jluai@outlook.com](ypchang_jluai@outlook.com); Xu Wang, [xwang22@mails.jlu.edu.cn](xwang22@mails.jlu.edu.cn), School of Artificial  \nIntelligence, Jilin University, 2699 Qianjin St, Changchun, China, 130012; Jindong Wang, Microsoft Research Asia, Beijing, China, [Jindong.wang@microsoft.com](Jindong.wang@microsoft.com); Yuan Wu, School of Artificial Intelligence, Jilin University, Changchun, China, [yuanwu@jlu.edu.cn](yuanwu@jlu.edu.cn); Linyi Yang, Westlake University, Hangzhou, China; Kaijie Zhu, Institute of Automation, Chinese Academy of Sciences, Beijing, China; Hao Chen, Carnegie Mellon University, Pennsylvania, USA; Xiaoyuan Yi, Microsoft Research Asia, Beijing, China; Cunxiang Wang, Westlake University, Hangzhou, China; Yidong Wang, Peking University, Beijing, China; Wei Ye, Peking University, Beijing, China; Yue Zhang, Westlake University, Hangzhou, China; Yi Chang, School of Artificial Intelligence, Jilin University, Changchun, China; Philip S. Yu, University of Illinois at Chicago, Illinois, USA; Qiang Yang, Hong Kong University of Science and Technology, Kowloon, Hong Kong, China; Xing Xie, Microsoft Research Asia, Beijing, 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 ACM 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 permissions@acm.org](prior specific permission and/or a fee. Request permissions fr","cbCaiboZJaZaa6pP","https://ap.wps.com/l/cbCaiboZJaZaa6pP","pdf",1029796,45,"English","# Introduction\n## Evaluation tasks: what to evaluate\n## Evaluation methods and benchmarks: where and how to evaluate\n## Success and failure cases across tasks\n## Future challenges and outlook","[{\"question\":\"What are the three key dimensions used to structure LLM evaluation in the survey?\",\"answer\":\"The survey organizes evaluation into three dimensions: what to evaluate, where to evaluate (methods and benchmarks), and how to evaluate.\"},{\"question\":\"Which kinds 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 treat “where” and “how” evaluation questions?\",\"answer\":\"It addresses them by diving into evaluation methods and benchmarks, which are described as crucial components for assessing LLM performance.\"}]","A Survey on Evaluation of Large Language Models - A Survey on Evaluation | PDF",113]