Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.09801 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910827202740224 |
|---|---|
| author | Ramler, Rudolf Straubinger, Philipp Plösch, Reinhold Winkler, Dietmar |
| author_facet | Ramler, Rudolf Straubinger, Philipp Plösch, Reinhold Winkler, Dietmar |
| contents | The integration of Large Language Models (LLMs), such as ChatGPT and GitHub Copilot, into software engineering workflows has shown potential to enhance productivity, particularly in software testing. This paper investigates whether LLM support improves defect detection effectiveness during unit testing. Building on prior studies comparing manual and tool-supported testing, we replicated and extended an experiment where participants wrote unit tests for a Java-based system with seeded defects within a time-boxed session, supported by LLMs. Comparing LLM supported and manual testing, results show that LLM support significantly increases the number of unit tests generated, defect detection rates, and overall testing efficiency. These findings highlight the potential of LLMs to improve testing and defect detection outcomes, providing empirical insights into their practical application in software testing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_09801 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unit Testing Past vs. Present: Examining LLMs' Impact on Defect Detection and Efficiency Ramler, Rudolf Straubinger, Philipp Plösch, Reinhold Winkler, Dietmar Software Engineering The integration of Large Language Models (LLMs), such as ChatGPT and GitHub Copilot, into software engineering workflows has shown potential to enhance productivity, particularly in software testing. This paper investigates whether LLM support improves defect detection effectiveness during unit testing. Building on prior studies comparing manual and tool-supported testing, we replicated and extended an experiment where participants wrote unit tests for a Java-based system with seeded defects within a time-boxed session, supported by LLMs. Comparing LLM supported and manual testing, results show that LLM support significantly increases the number of unit tests generated, defect detection rates, and overall testing efficiency. These findings highlight the potential of LLMs to improve testing and defect detection outcomes, providing empirical insights into their practical application in software testing. |
| title | Unit Testing Past vs. Present: Examining LLMs' Impact on Defect Detection and Efficiency |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2502.09801 |