LLMs and Prompting for Unit Test Generation: A Large-Scale Evaluation
Unit testing, essential for identifying bugs, is often neglected due to time constraints. Automated test generation tools exist but typically lack readability and require developer intervention. Large Language Models (LLMs) like GPT and Mistral show potential in test generation, but their effectiveness remains unclear.
Authors
- Jacques Klein (ORCID: https://orcid.org/0000-0003-4052-475X)
- Abdoul Kader Kaboré (ORCID: https://orcid.org/0000-0002-3151-9433)
- Anil Koyuncu (ORCID: https://orcid.org/0000-0001-6975-6752)
- Yewei Song (ORCID: https://orcid.org/0000-0002-6314-7515)
- David Lo (ORCID: https://orcid.org/0000-0002-4367-7201)
- Tegawendé François Bissyandé (ORCID: https://orcid.org/0000-0001-7270-9869)
- Wendkûuni C. Ouédraogo (ORCID: https://orcid.org/0009-0009-7312-6273)
- Haoye Tian (ORCID: https://orcid.org/0000-0002-8049-3997)
Institutions
- The University of Melbourne (AU)
- Bilkent University (TR)
- University of Luxembourg (LU)
- Singapore Management University (SG)
Publication Details
- Published
- 2024-10-18
- DOI
- https://doi.org/10.1145/3691620.3695330
- Citations
- 7
- Primary Topic
- Software Testing and Debugging Techniques
- Type
- article
- Field-Weighted Citation Impact
- 3.40
Funders
- Fonds National de la Recherche Luxembourg