@inproceedings{483daf72587e42cb9e93b92501bc8e45,
title = "On Teaching Novices Computational Thinking by Utilizing Large Language Models Within Assessments",
abstract = "Novice programmers often struggle to develop computational thinking (CT) skills in introductory programming courses. This study investigates the use of Large Language Models (LLMs) to provide scalable, strategy-driven feedback to teach CT. Through think-aloud interviews with 17 students solving code comprehension and writing tasks, we found that LLMs effectively guided decomposition and program development tool usage. Challenges included students seeking direct answers or pasting feedback without considering suggested strategies. We discuss how instructors should integrate LLMs into assessments to support students{\textquoteright} learning of CT.",
keywords = "Large Language Models, code comprehension, debuggers, execution",
author = "Mohammed Hassan and Yuxuan Chen and Paul Denny and Craig Zilles",
note = "Publisher Copyright: {\textcopyright} 2025 Copyright held by the owner/author(s).; 56th Annual SIGCSE Technical Symposium on Computer Science Education, SIGCSE TS 2025 ; Conference date: 26-02-2025 Through 01-03-2025",
year = "2025",
month = feb,
day = "18",
doi = "10.1145/3641554.3701906",
language = "English (US)",
series = "SIGCSE TS 2025 - Proceedings of the 56th ACM Technical Symposium on Computer Science Education",
publisher = "Association for Computing Machinery",
pages = "471--477",
booktitle = "SIGCSE TS 2025 - Proceedings of the 56th ACM Technical Symposium on Computer Science Education",
address = "United States",
}