About this document

LLMs for Automated Unit Test Generation by joashjohnson2004 is a document available to read on EtoBox.

This paper evaluates the use of Large Language Models (LLMs) for automated unit test generation, specifically through a tool called TESTPILOT for JavaScript. The study finds that TESTPILOT achieves a median statement coverage of 70.2% and branch coverage of 52.8%, outperforming traditional test generation techniques. The results suggest that careful prompt crafting is sufficient for effective test generation without requiring additional training or manual effort.

Author

joashjohnson2004

Language

EN