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
  • [21] Enhanced automated code vulnerability repair using large language models
    de-Fitero-Dominguez, David
    Garcia-Lopez, Eva
    Garcia-Cabot, Antonio
    Martinez-Herraiz, Jose-Javier
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 138
  • [22] VHDL-Eval: A Framework for Evaluating Large Language Models in VHDL Code Generation
    Vijayaraghavan, Prashanth
    Shi, Luyao
    Ambrogio, Stefano
    Mackin, Charles
    Nitsure, Apoorva
    Beymer, David
    Degan, Ehsan
    2024 IEEE LLM AIDED DESIGN WORKSHOP, LAD 2024, 2024,
  • [23] Balancing Security and Correctness in Code Generation: An Empirical Study on Commercial Large Language Models
    Black, Gavin S.
    Rimal, Bhaskar P.
    Vaidyan, Varghese Mathew
    IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2025, 9 (01): : 419 - 430
  • [24] Enhancing Large Language Models-Based Code Generation by Leveraging Genetic Improvement
    Pinna, Giovanni
    Ravalico, Damiano
    Rovito, Luigi
    Manzoni, Luca
    De Lorenzo, Andrea
    GENETIC PROGRAMMING, EUROGP 2024, 2024, 14631 : 108 - 124
  • [25] Investigating legal question generation using large language models
    Deroy, Aniket
    Ghosh, Kripabandhu
    Ghosh, Saptarshi
    ARTIFICIAL INTELLIGENCE AND LAW, 2025,
  • [26] Autoregressive Self-Evaluation: A Case Study of Music Generation Using Large Language Models
    Banat, Rerker
    Colton, Simon
    2023 IEEE CONFERENCE ON ARTIFICIAL INTELLIGENCE, CAI, 2023, : 264 - 265
  • [27] Unveiling the Impact of Large Language Models on Student Learning: A Comprehensive Case Study
    Zdravkova, Katerina
    Dalipi, Fisnik
    Ahlgren, Fredrik
    Ilijoski, Bojan
    Ohlsson, Tobias
    2024 IEEE GLOBAL ENGINEERING EDUCATION CONFERENCE, EDUCON 2024, 2024,
  • [28] Automation of Network Configuration Generation using Large Language Models
    Chakraborty, Supratim
    Chitta, Nithin
    Sundaresan, Rajesh
    2024 20TH INTERNATIONAL CONFERENCE ON NETWORK AND SERVICE MANAGEMENT, CNSM 2024, 2024,
  • [29] Large Language Model-based Test Case Generation for GP Agents
    Jorgensen, Steven
    Nadizar, Giorgia
    Pietropolli, Gloria
    Manzoni, Luca
    Medvet, Eric
    O'Reilly, Una-May
    Hemberg, Erik
    PROCEEDINGS OF THE 2024 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, GECCO 2024, 2024, : 914 - 923
  • [30] Generation of Robot Manipulation Plans Using Generative Large Language Models
    Toberg, Jan-Philipp
    Cimiano, Philipp
    2023 SEVENTH IEEE INTERNATIONAL CONFERENCE ON ROBOTIC COMPUTING, IRC 2023, 2023, : 190 - 197