[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-585378-105":59,"doc-detail-585378-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","toward-llm-supported-automated-assessment-of-critical-thinking-subskills","Toward LLM-supported Automated Assessment of Critical Thinking Subskills","","As the world becomes saturated with AI-generated content, disinformation, and algorithmic persuasion, critical thinking—evaluating evidence, detecting unreliable claims, and exercising independent judgment—becomes an essential human competency. The paper examines the feasibility of measuring critical thinking “subskills” underlying critical thinking. It presents an authentic task and compares automated scoring methods (zero-shot prompting, few-shot prompting, and supervised fine-tuning) across multiple large language models.",{"@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/toward-llm-supported-automated-assessment-of-critical-thinking-subskills/585378/",{"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/toward-llm-supported-automated-assessment-of-critical-thinking-subskills/585378.png","ImageObject",300,407,{"name":92,"@type":93},"Aria Callaghan","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-10-15",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 does the paper aim to achieve regarding critical thinking?","Question",{"text":112,"@type":113},"It investigates whether critical thinking can be supported by measuring underlying “subskills” and assessing them using automated methods.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Which automated scoring approaches are evaluated?",{"text":117,"@type":113},"The study evaluates zero-shot prompting, few-shot prompting, and supervised fine-tuning for automated scoring.",{"name":119,"@type":110,"acceptedAnswer":120},"How do the results compare across the evaluated language models and subskills?",{"text":121,"@type":113},"Fine-tuning Llama 3.1 8B yields the best overall results, performing especially well when subskill proficiency levels are highly separable, while it is weaker for subtle distinctions or imbalanced labels.","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},585378,1792190410,{"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,"preview_page_count":4},962084926284,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","Toward LLM-supported Automated Assessment of Critical  \nThinking Subskills  \nMarisa C. Peczuh* University of Minnesota [peczu001@umn.edu](peczu001@umn.edu)  \nNischal Ashok Kumar*  \nUniversity of Massachusetts, Amherst  \n[nashokkumar@umass.edu](nashokkumar@umass.edu)  \nRyan S. Baker  \nAdelaide University [ryanshaunbaker@gmail.com](ryanshaunbaker@gmail.com)  \nBlair Lehman  \nBrighter Research [blair.lehman@gmail.com](blair.lehman@gmail.com)  \nPayu Wittawatolarn  \nUniversity of Massachusetts, Amherst  \n[pwittawatola@umass.edu](pwittawatola@umass.edu)  \nDanielle Eisenberg Educational Testing Service  \n[deisenberg@ets.org](deisenberg@ets.org)  \nKushaan Naskar University of Massachusetts,  \nAmherst [knaskar@umass.edu](knaskar@umass.edu)  \nCaitlin Mills  \nUniversity of Minnesota [cmills@umn.edu](cmills@umn.edu)  \nKeerthi Chebrolu University of Massachusetts,  \nAmherst [kchebrolu@umass.edu](kchebrolu@umass.edu)  \nSudhip Nashi  \nUniversity of Massachusetts, Amherst  \n[snashi@umass.edu](snashi@umass.edu)  \nCadence Young  \nUniversity of Massachusetts, Amherst  \n[cadenceyoung@umass.edu](cadenceyoung@umass.edu)  \nBrayden Liu  \nUniversity of Massachusetts, Amherst  \n[zliu@nutrition.umass.edu](zliu@nutrition.umass.edu)  \nSherry Lachman  \nAugmentED, Advanced Education Research and Development Fund  \n[slachman@aerdf.org](slachman@aerdf.org)  \nAndrew Lan  \nUniversity of Massachusetts, Amherst  \n[andrewlan@cs.umass.edu](andrewlan@cs.umass.edu)  \n*Joint first authors with equal contribution  \nABSTRACT  \nAs the world becomes increasingly saturated with AI-generated content, disinformation, and algorithmic persuasion, critical thinking – the capacity to evaluate evidence, detect unreliable claims, and exercise independent judgment – is becoming a defining human skill. Developing critical thinking skills through timely assessment and feedback is crucial; however, there has not been extensive work in educational data mining on defining, measuring, and supporting critical thinking. In this paper, we investigate the feasibility of measuring “subskills” that underlie critical thinking. We ground our work in an authentic task where students operationlzrsacilh, tilgAokwiutimnr, anatkav, eBlisrsaLyesh.mne,  eavnleisnbgd,inailuiriillbsa, sdayuonWiataweasttoalins,heuskaials Naskar, Keerthi Chebrolu, Sudhip Nashi, Cadence Young, Brayden Liu, Sherry Lachman, and Andrew Lan. Toward LLM-supported Automated Assessment of Critical Thinking Subskills. In Anthony Botelho, Maria Mercedes T. Rodrigo, Adish Singla, Hiroaki Ogata, Hyojeong So, and Young Hoan Cho (eds.) Proceedings of the 19th International Conference on Educational Data Mining, Seoul, Republic of Korea, June, 2026, pp. 340–352. International Educational Data Mining Society (2026) .  \n© 2026 Copyright is held by the author(s) . This work is distributed under the Creative Commons Attribution NonCommercial NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license. [https://doi.org/10.5281/zenodo.21039869](https://doi.org/10.5281/zenodo.21039869)  \nprogression and completed human coding for a corpus of student essays. We then evaluated three distinct approaches to automated scoring: zero-shot prompting, few-shot prompting, and supervised fine-tuning, implemented across three large language models (GPT-5, Llama 3.1 8B, and ModernBERT). Fine-tuning Llama 3.1 8B achieved the best results and demonstrated particular strength on subskills with highly separable proficiency levels with balanced labels across levels, while lower performance was observed for subskills that required detection of subtle distinctions between proficiency levels or imbalanced labels. Our exploratory work represents an initial step toward scalable assessment of critical thinking skills across authentic educational contexts. Future research should continue to combine automated critical thinking assessment with human validation to more accurately detect and measure dynamic, higher-order thinking skills.  \nKeywords  \nCritical thinking, 21st c","cbCaiouVEz61HOUn","https://ap.wps.com/l/cbCaiouVEz61HOUn","pdf",505529,13,"English","# Abstract\n# Keywords\n# 1. Introduction\n## Background and motivation\n## Challenges in operationalizing critical thinking","[{\"question\":\"What does the paper aim to achieve regarding critical thinking?\",\"answer\":\"It investigates whether critical thinking can be supported by measuring underlying “subskills” and assessing them using automated methods.\"},{\"question\":\"Which automated scoring approaches are evaluated?\",\"answer\":\"The study evaluates zero-shot prompting, few-shot prompting, and supervised fine-tuning for automated scoring.\"},{\"question\":\"How do the results compare across the evaluated language models and subskills?\",\"answer\":\"Fine-tuning Llama 3.1 8B yields the best overall results, performing especially well when subskill proficiency levels are highly separable, while it is weaker for subtle distinctions or imbalanced labels.\"}]","Toward LLM-supported Automated Assessment of Critical Thinking Subskills | PDF",1792054557,33]