On the Effectiveness of LLMs for Manual Test Verifications

TL;DR

This paper investigates the use of Large Language Models to generate manual test verifications, comparing their effectiveness and professional acceptance, and providing a dataset of generated verifications for future research.

Contribution

It presents a comprehensive evaluation of multiple LLMs for test verification generation and releases a large dataset of generated verifications for the software testing community.

Findings

Open-source LLMs perform comparably to closed-source models.

Professional testers agree with generated verifications slightly above 40%.

Some generated verifications outperform original ones, but hallucinations pose challenges.

Abstract

Background: Manual testing is vital for detecting issues missed by automated tests, but specifying accurate verifications is challenging. Aims: This study aims to explore the use of Large Language Models (LLMs) to produce verifications for manual tests. Method: We conducted two independent and complementary exploratory studies. The first study involved using 2 closed-source and 6 open-source LLMs to generate verifications for manual test steps and evaluate their similarity to original verifications. The second study involved recruiting software testing professionals to assess their perception and agreement with the generated verifications compared to the original ones. Results: The open-source models Mistral-7B and Phi-3-mini-4k demonstrated effectiveness and consistency comparable to closed-source models like Gemini-1.5-flash and GPT-3.5-turbo in generating manual test verifications. However, the agreement level among professional testers was slightly above 40%, indicating both promise and room for improvement. While some LLM-generated verifications were considered better than the originals, there were also concerns about AI hallucinations, where verifications significantly deviated from expectations. Conclusion: We contributed by generating a dataset of 37,040 test verifications using 8 different LLMs. Although the models show potential, the relatively modest 40% agreement level highlights the need for further refinement. Enhancing the accuracy, relevance, and clarity of the generated verifications is crucial to ensure greater reliability in real-world testing scenarios.