No More Manual Tests? Evaluating and Improving ChatGPT for Unit Test Generation

TL;DR

This paper empirically evaluates ChatGPT's ability to generate unit tests, revealing promising results in test quality but highlighting correctness issues, and proposes an improved approach called ChatTESTER that enhances test generation success.

Contribution

It provides the first systematic evaluation of ChatGPT for unit test generation and introduces ChatTESTER, a method to improve test correctness and coverage.

Findings

ChatGPT generates tests with comparable coverage and readability to manual tests.

Generated tests still face correctness issues like compilation errors and failures.

ChatTESTER improves the number of compilable and correct tests significantly.

Abstract

Unit testing is essential in detecting bugs in functionally-discrete program units. Manually writing high-quality unit tests is time-consuming and laborious. Although traditional techniques can generate tests with reasonable coverage, they exhibit low readability and cannot be directly adopted by developers. Recent work has shown the large potential of large language models (LLMs) in unit test generation, which can generate more human-like and meaningful test code. ChatGPT, the latest LLM incorporating instruction tuning and reinforcement learning, has performed well in various domains. However, It remains unclear how effective ChatGPT is in unit test generation. In this work, we perform the first empirical study to evaluate ChatGPT's capability of unit test generation. Specifically, we conduct a quantitative analysis and a user study to systematically investigate the quality of its generated tests regarding the correctness, sufficiency, readability, and usability. The tests generated by ChatGPT still suffer from correctness issues, including diverse compilation errors and execution failures. Still, the passing tests generated by ChatGPT resemble manually-written tests by achieving comparable coverage, readability, and even sometimes developers' preference. Our findings indicate that generating unit tests with ChatGPT could be very promising if the correctness of its generated tests could be further improved. Inspired by our findings above, we propose ChatTESTER, a novel ChatGPT-based unit test generation approach, which leverages ChatGPT itself to improve the quality of its generated tests. ChatTESTER incorporates an initial test generator and an iterative test refiner. Our evaluation demonstrates the effectiveness of ChatTESTER by generating 34.3% more compilable tests and 18.7% more tests with correct assertions than the default ChatGPT.