Improving the Readability of Automatically Generated Tests using Large Language Models

TL;DR

This paper presents a method that enhances the readability of automatically generated tests by improving variable and test names using large language models, while maintaining their original effectiveness in code coverage.

Contribution

It introduces a technique to improve test readability by refining names in search-based generated tests using LLMs without sacrificing coverage.

Findings

Readability of tests improved to match developer-written tests

Semantic preservation of test semantics confirmed across multiple runs

Human study shows tests are as readable as those written by developers

Abstract

Search-based test generators are effective at producing unit tests with high coverage. However, such automatically generated tests have no meaningful test and variable names, making them hard to understand and interpret by developers. On the other hand, large language models (LLMs) can generate highly readable test cases, but they are not able to match the effectiveness of search-based generators, in terms of achieved code coverage. In this paper, we propose to combine the effectiveness of search-based generators with the readability of LLM generated tests. Our approach focuses on improving test and variable names produced by search-based tools, while keeping their semantics (i.e., their coverage) unchanged. Our evaluation on nine industrial and open source LLMs show that our readability improvement transformations are overall semantically-preserving and stable across multiple repetitions. Moreover, a human study with ten professional developers, show that our LLM-improved tests are as readable as developer-written tests, regardless of the LLM employed.