Evaluating the Application of Large Language Models to Generate Feedback in Programming Education

被引：2

作者：

Jacobs, Sven ^{[1
]}

Jaschke, Steffen ^{[1
]}

机构：

[1] Univ Siegen, Comp Sci Educ, Siegen, Germany

来源：

2024 IEEE GLOBAL ENGINEERING EDUCATION CONFERENCE, EDUCON 2024 | 2024年

关键词：

D O I：

10.1109/EDUCON60312.2024.10578838

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

This study investigates the application of large language models, specifically GPT-4, to enhance programming education. The research outlines the design of a web application that uses GPT-4 to provide feedback on programming tasks, without giving away the solution. A web application for working on programming tasks was developed for the study and evaluated with 51 students over the course of one semester. The results show that most of the feedback generated by GPT-4 effectively addressed code errors. However, challenges with incorrect suggestions and hallucinated issues indicate the need for further improvements.

引用

页数：5

共 50 条

[41] Evaluating large language models as agents in the clinic
Mehandru, Nikita
Miao, Brenda Y.
Almaraz, Eduardo Rodriguez
Sushil, Madhumita
Butte, Atul J.
Alaa, Ahmed
NPJ DIGITAL MEDICINE, 2024, 7 (01)
[42] Large Language Models in Robot Programming Potential in the programming of industrial robots
Syniawa, Daniel
Ates, Baris
Boshoff, Marius
Kuhlenkoetter, Bernd
ATP MAGAZINE, 2024, (6-7):
[43] Teach AI How to Code: Using Large Language Models as Teachable Agents for Programming Education
Jin, Hyoungwook
Lee, Seonghee
Shin, Hyungyu
Kim, Juho
PROCEEDINGS OF THE 2024 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYTEMS, CHI 2024, 2024,
[44] AI-Tutoring in Software Engineering Education Experiences with Large Language Models in Programming Assessments
Frankford, Eduard
Sauerwein, Clemens
Bassner, Patrick
Krusche, Stephan
Breu, Ruth
2024 ACM/IEEE 44TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING: SOFTWARE ENGINEERING EDUCATION AND TRAINING, ICSE-SEET 2024, 2024, : 309 - 319
[45] Evaluating large language models as patient education tools for inflammatory bowel disease: A comparative study
Zhang, Yan
Wan, Xiao-Han
Kong, Qing-Zhou
Liu, Han
Liu, Jun
Guo, Jing
Yang, Xiao-Yun
Zuo, Xiu-Li
Li, Yan-Qing
WORLD JOURNAL OF GASTROENTEROLOGY, 2025, 31 (06)
[46] Promises and Pitfalls: Using Large Language Models to Generate Visualization Items
Cui, Yuan
Ge, Lily W.
Ding, Yiren
Harrison, Lane
Yang, Fumeng
Kay, Matthew
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2025, 31 (01) : 1094 - 1104
[47] Aligning Large Language Models through Synthetic Feedback
Kim, Sungdong
Bae, Sanghwan
Shin, Jamin
Kang, Soyoung
Kwak, Donghyun
Yoo, Kang Min
Seo, Minjoon
2023 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2023), 2023, : 13677 - 13700
[48] Using Large Language Models to Facilitate the Utilization of Specific Application Programming Interfaces in Learning Factories
Dorka, Frithjof
El Otmani, Kaoutar
Hentsch, Maximilian
Kunster, Nils
Palm, Daniel
LEARNING FACTORIES OF THE FUTURE, VOL 2, CLF 2024, 2024, 1060 : 346 - 352
[49] Using Large Language Models to Generate JUnit Tests: An Empirical Study
Siddiq, Mohammed Latif
Santos, Joanna C. S.
Tanvir, Ridwanul Hasan
Ulfat, Noshin
Al Rifat, Fahmid
Lopes, Vinicius Carvalho
PROCEEDINGS OF 2024 28TH INTERNATION CONFERENCE ON EVALUATION AND ASSESSMENT IN SOFTWARE ENGINEERING, EASE 2024, 2024, : 313 - 322
[50] Plan, Generate and Match: Scientific Workflow Recommendation with Large Language Models
Gu, Yang
Cao, Jian
Guo, Yuan
Qian, Shiyou
Guan, Wei
SERVICE-ORIENTED COMPUTING, ICSOC 2023, PT I, 2023, 14419 : 86 - 102

← 1 2 3 4 5 →