[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-488120-105":59,"doc-detail-488120-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","empirical-study-of-large-language-models-as-automated-essay-scoring-tools-in-english-composition-taking-toefl-independent-writing-task-for-example","Empirical Study of Large Language Models as Automated Essay Scoring Tools in English Composition - Taking TOEFL Independent Writing Task for Example","","Large language models demonstrate strong capabilities in natural language generation, reasoning, and comprehension, motivating their use in automated essay scoring. This study constructs prompts and comments aligned with the scoring criteria from the official TOEFL guide to evaluate ChatGPT as an automated essay scoring tool. It contrasts with prior AES methods that rely on deep learning and fine-tuning but struggle under small-sample conditions. Empirical results show ChatGPT can perform operational automated scoring, though a regression effect appears; prompt design requires substantial domain expertise and technical proficiency.",{"@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/empirical-study-of-large-language-models-as-automated-essay-scoring-tools-in-english-composition-taking-toefl-independent-writing-task-for-example/488120/",{"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/empirical-study-of-large-language-models-as-automated-essay-scoring-tools-in-english-composition-taking-toefl-independent-writing-task-for-example/488120.png","ImageObject",300,407,{"name":92,"@type":93},"OmBimo","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-12","2026-09-30",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the main goal of this study?","Question",{"text":112,"@type":113},"To build prompts and feedback aligned with TOEFL scoring criteria and assess ChatGPT’s capabilities and limitations in automated essay scoring for English composition.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does this research approach automated essay scoring with ChatGPT?",{"text":117,"@type":113},"It uses ChatGPT to evaluate provided essays while formulating prompts and feedback based on writing elements in the official TOEFL guide, then derives assessment metrics during experiments.",{"name":119,"@type":110,"acceptedAnswer":120},"What do the empirical findings indicate about ChatGPT for essay scoring?",{"text":121,"@type":113},"ChatGPT can provide operational functionality for automated essay scoring, but the results show a regression effect, and effective prompting depends on domain expertise and technical proficiency.","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},488120,1790828199,{"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":34,"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":144,"read_time":145},962090893581,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Empirical Study of Large Language Models as Automated Essay Scoring Tools in English Composition——Taking TOEFL Independent Writing Task for Example  \nWei Xia 1 , Shaoguang Mao2 , Chanjing Zheng 1,3  \nAuthor Note  \n1 Department of Educational Psychology of Faculty of Education, East China Normal University, Shanghai, China;  \n2 Microsoft Research Asia, Beijing, China;  \n3 Shanghai Institute of Artificial Intelligence Education, East China Normal University, Shanghai, China.  \nCorrespondence concerning this article should be addressed to Chanjing Zheng, Department of Educational Psychology of Faculty of Education and Shanghai Institute of Artificial Intelligence Education, East China Normal University, Shanghai, 200062; China.  \nEmail: [chjzheng@dep.ecnu.edu.cn](chjzheng@dep.ecnu.edu.cn)  \nAbstract  \nLarge language models have demonstrated exceptional capabilities in tasks involving natural language generation, reasoning, and comprehension. This study aims to construct prompts and comments grounded in the diverse scoring criteria delineated within the official TOEFL guide. The primary objective is to assess the capabilities and constraints of ChatGPT, a prominent representative of large language models, within the context of automated essay scoring.  \nThe prevailing methodologies for automated essay scoring involve the utilization of deep neural networks, statistical machine learning techniques, and fine-tuning pre-trained models. However, these techniques face challenges when applied to different contexts or subjects, primarily due to their substantial data requirements and limited adaptability to small sample sizes. In contrast, this study employs ChatGPT to conduct an automated evaluation of English essays, even with a small sample size, employing an experimental approach.  \nThe empirical findings indicate that ChatGPT can provide operational functionality for automated essay scoring, although the results exhibit a regression effect. It is imperative to underscore that the effective design and implementation of ChatGPT prompts necessitate a profound domain expertise and technical proficiency, as these prompts are subject to specific threshold criteria.  \nKeywords: ChatGPT, Automated Essay Scoring, Prompt Learning, TOEFL Independent Writing Task  \nEmpirical Study of Large Language Models as Automated Essay Scoring Tools in English Composition——Taking TOEFL Independent Writing Task for Example  \nIntroduction  \nWriting practice plays a pivotal role in the language acquisition process. With a growing number of students, the workload for educators tasked with reviewing student essays has surged significantly. Consequently, Automated Essay Scoring (AES) methods have gained widespread popularity all around the world. AES systems offer the potential to expedite the essay correction process, furnish feedback notes, and assist students in identifying crucial elements of writing, thereby enhancing their writing proficiency. At the heart of automated essay scoring systems lies the core technology known as Natural Language Processing (NLP), an interdisciplinary field encompassing linguistics, computer science, and related domains. NLP investigations encompass diverse linguistic units, such as characters, words, phrases and paragraphs, along with a spectrum of activities, including natural language processing, comprehension, and generation. Given the prevailing state of natural language technology at the time of this research, automated essay scoring systems are categorized into five developmental stages.  \nHistorically, the development of automated essay scoring technology has been largely contingent on advancements in computer technology, predating the introduction of ChatGPT (Chat Generative Pretrained Transformer) . Although significant technical progress has led to an incremental improvement in the quality of automated essay scoring, several significant challenges persist. Existing research methods demonstrate subpar performance in sc","cbCaiq3sqcPfuk7X","https://ap.wps.com/l/cbCaiq3sqcPfuk7X","pdf",1751919,41,"English","# Introduction\n## Background and motivation for automated essay scoring\n## ChatGPT and its role in automated scoring\n# Overview of the Development of Automated Essay Scoring Systems from the Perspective of Natural Language Processing\n## Early foundations and NLP underpinnings","[{\"question\":\"What is the main goal of this study?\",\"answer\":\"To build prompts and feedback aligned with TOEFL scoring criteria and assess ChatGPT’s capabilities and limitations in automated essay scoring for English composition.\"},{\"question\":\"How does this research approach automated essay scoring with ChatGPT?\",\"answer\":\"It uses ChatGPT to evaluate provided essays while formulating prompts and feedback based on writing elements in the official TOEFL guide, then derives assessment metrics during experiments.\"},{\"question\":\"What do the empirical findings indicate about ChatGPT for essay scoring?\",\"answer\":\"ChatGPT can provide operational functionality for automated essay scoring, but the results show a regression effect, and effective prompting depends on domain expertise and technical proficiency.\"}]","Empirical Study of Large Language Models as Automated Essay Scoring Tools in English Composition - Taking TOEFL Independent Writing Task for Example | PDF",1790810399,103]