What question did this study set out to answer?

May 1, 2026Cogent EducationOpen Access

Evaluating the impact of Large Language Models on problem-solving skills in programming debugging of IT undergraduates

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial evaluates LLMs' effect on debugging skills in IT undergraduates, suggesting balanced integration for optimal learning.

To investigate the impact of Large Language Models on problem-solving skills in programming debugging among IT undergraduates.
Pre-, mid-, and post-experimental design with pre-test, mid-test, and two post-tests performed on 87 students.
Performance assessed with and without LLM assistance, stratified by gender, academic level, A/L stream, Z-score, and GPA.
Statistical analysis of debugging accuracy and task efficiency before and after LLM integration.
Debugging accuracy improved from 46.53% in the pre-test to 69.51% in the post-test (Prior).
Task completion time decreased from 18 minutes to 10 minutes after using LLM assistance.
Moderate transferability to new problems was observed, with a post-test (Recent) accuracy of 58.40%.

Riztha et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark