Understanding on the Edge: LLM-generated Boundary Test Explanations

TL;DR

This study evaluates GPT-4.1's ability to generate boundary explanations for software testing, finding that while generally helpful, explanations need clearer structure and actionable content for practical use.

Contribution

It provides an empirical assessment of LLM-generated boundary explanations and proposes design criteria for improving their usefulness in software testing.

Findings

63.5% positive ratings for explanations

Participants prefer structured, authoritative, and tailored explanations

Actionable examples are crucial for debugging support

Abstract

Boundary value analysis and testing (BVT) is fundamental in software quality assurance because faults tend to cluster at input extremes, yet testers often struggle to understand and justify why certain input-output pairs represent meaningful behavioral boundaries. Large Language Models (LLMs) could help by producing natural-language rationales, but their value for BVT has not been empirically assessed. We therefore conducted an exploratory study on LLM-generated boundary explanations: in a survey, twenty-seven software professionals rated GPT-4.1 explanations for twenty boundary pairs on clarity, correctness, completeness and perceived usefulness, and six of them elaborated in follow-up interviews. Overall, 63.5% of all ratings were positive (4-5 on a five-point Likert scale) compared to 17% negative (1-2), indicating general agreement but also variability in perceptions. Participants favored explanations that followed a clear structure, cited authoritative sources, and adapted their depth to the reader's expertise; they also stressed the need for actionable examples to support debugging and documentation. From these insights, we distilled a seven-item requirement checklist that defines concrete design criteria for future LLM-based boundary explanation tools. The results suggest that, with further refinement, LLM-based tools can support testing workflows by making boundary explanations more actionable and trustworthy.