| Title |
Quality evaluation of large language models generated unit tests: influence of structured output / |
| Authors |
Zapkus, Dovydas Marius ; Slotkienė, Asta |
| DOI |
10.15388/MITT.2025.32 |
| Full Text |
|
| Is Part of |
Lietuvos magistrantų informatikos ir IT tyrimai: konferencijos darbai, 2025 m. gegužės 13 d... Vilnius : Vilniaus universiteto leidykla. 2025, p. 281-288.. eISSN 2783-784X |
| Keywords [eng] |
large language model ; unit test ; quality metrics ; structured prompt output |
| Abstract [eng] |
Unit testing is critical in software quality assurance, and large language models (LLMs) offer an approach to automate this process. This paper evaluates the quality of unit tests generated by large language models using structured output prompts. The research applied six LLMs in generating unit tests across different classes of cyclomatic complexity of C# focal methods. The experiment result shows that LLMs generated results according to a strict structure output (Arrange-Act-Assert pattern) that significantly influences the quality of the generated unit tests. |
| Published |
Vilnius : Vilniaus universiteto leidykla |
| Type |
Conference paper |
| Language |
English |
| Publication date |
2025 |
| CC license |
|
