Using Large Language Models to Generate JUnit Tests: An Empirical Study

arXiv:2305.00418v4 Announce Type: replace-cross
Abstract: A code generation model generates code by taking a prompt from a code comment, existing code, or a combination of both. Although code generation models (e.g., GitHub Copilot) are increasingly being adopted in practice, it is unclear whether they can successfully be used for unit test generation without fine-tuning for a strongly typed language like Java. To fill this gap, we investigated how well three models (Codex, GPT-3.5-Turbo, and StarCoder) can generate unit tests. We …

abstract arxiv code code generation combination copilot cs.lg cs.se generate github language language models large language large language models practice prompt study tests type