Using Large Language Models for Student-Code Guided Test Case Generation in Computer Science Education

被引:0
作者
Kumar, Nischal Ashok [1 ]
Lan, Andrew S. [1 ]
机构
[1] Univ Massachusetts Amherst, Amherst, MA 01003 USA
来源
AI FOR EDUCATION WORKSHOP | 2024年 / 257卷
关键词
Computer Science Education; Large Language Models; Test Case Generation;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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 knowledge and 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 test cases 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.
引用
收藏
页码:170 / 178
页数:9
相关论文
共 50 条
  • [1] Automatic Unit Test Code Generation Using Large Language Models
    Ocal, Akdeniz Kutay
    Keskinoz, Mehmet
    32ND IEEE SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE, SIU 2024, 2024,
  • [2] The impact of large language models on computer science student writing
    Katerina Zdravkova
    Bojan Ilijoski
    International Journal of Educational Technology in Higher Education, 22 (1)
  • [3] Multi-stage guided code generation for Large Language Models
    Han, Yewei
    Lyu, Chen
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2025, 139
  • [4] Large Language Models in Computer Science Education: A Systematic Literature Review
    Raihan, Nishat
    Siddiq, Mohammed Latif
    Santos, Joanna C. S.
    Zampieri, Marcos
    PROCEEDINGS OF THE 56TH ACM TECHNICAL SYMPOSIUM ON COMPUTER SCIENCE EDUCATION, SIGCSE TS 2025, VOL 2, 2025, : 938 - 944
  • [5] Large Language Models in Computer Science Education: A Systematic Literature Review
    Raihan, Nishat
    Siddiq, Mohammed Latif
    Santos, Joanna C. S.
    Zampieri, Marcos
    PROCEEDINGS OF THE 56TH ACM TECHNICAL SYMPOSIUM ON COMPUTER SCIENCE EDUCATION, SIGCSE TS 2025, VOL 1, 2025, : 938 - 944
  • [6] Using Large Language Models for Automated Grading of Student Writing about Science
    Impey, Chris
    Wenger, Matthew
    Garuda, Nikhil
    Golchin, Shahriar
    Stamer, Sarah
    INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE IN EDUCATION, 2025,
  • [7] Can Small Language Models With Retrieval-Augmented Generation Replace Large Language Models When Learning Computer Science?
    Liu, Suqing
    Yu, Zezhu
    Huang, Feiran
    Bulbulia, Yousef
    Bergen, Andreas
    Liut, Michael
    PROCEEDINGS OF THE 2024 CONFERENCE INNOVATION AND TECHNOLOGY IN COMPUTER SCIENCE EDUCATION, VOL 1, ITICSE 2024, 2024, : 388 - 393
  • [8] Knowledge-Aware Code Generation with Large Language Models
    Huang, Tao
    Sun, Zhihong
    Jin, Zhi
    Li, Ge
    Lyu, Chen
    PROCEEDINGS 2024 32ND IEEE/ACM INTERNATIONAL CONFERENCE ON PROGRAM COMPREHENSION, ICPC 2024, 2024, : 52 - 63
  • [9] Large language models for causal hypothesis generation in science
    Cohrs, Kai-Hendrik
    Diaz, Emiliano
    Sitokonstantinou, Vasileios
    Varando, Gherardo
    Camps-Valls, Gustau
    MACHINE LEARNING-SCIENCE AND TECHNOLOGY, 2025, 6 (01):
  • [10] Self-Planning Code Generation with Large Language Models
    Jiang, Xue
    Dong, Yihong
    Wang, Lecheng
    Fang, Zheng
    Shang, Qiwei
    Li, Ge
    Jin, Zhi
    Jiao, Wenpin
    ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY, 2024, 33 (07)