2024-08-09-kumar24.md

title	booktitle	year	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Using Large Language Models for Student-Code Guided Test Case Generation in Computer Science Education	Proceedings of the 2024 AAAI Conference on Artificial Intelligence	2024	In computer science education, test cases are an integral part of programming assignments since they can be used as assessment items to test students' programming knowledgeand provide personalized feedback on student-written code. The goal of our work is to propose a fully automated approach for test case generation that can accurately measure student knowledge, which is important for two reasons. First, manually constructing testcases requires expert knowledge and is a labor-intensive process. Second, developing test cases for students, especially those who are novice programmers, is significantly different from those oriented toward professional-level software developers. Therefore, we need an automated process for test case generation to assess student knowledge and provide feedback. In this work, we propose a large language model-based approach to automatically generate test cases and show that they are good measures of student knowledge, using a publicly available dataset that contains student-written Java code. We also discuss future research directions centered on using test cases to help students.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	kumar24	0	Using Large Language Models for Student-Code Guided Test Case Generation in Computer Science Education	170	179	170-179	170	false	Ashok Kumar, Nischal and Andrew S., Lan	given family Nischal Ashok Kumar given family Andrew S. Lan	2024-08-09		Proceedings of the 2024 AAAI Conference on Artificial Intelligence	257	inproceedings	date-parts 2024 8 9	https://raw.githubusercontent.com/mlresearch/v257/main/assets/kumar24/kumar24.pdf