LESS is More: Guiding LLMs for Formal Requirement and Test Case Generation

Large Language Models (LLMs) demonstrate impressive in-context reasoning capabilities; however, generating structured outputs remains challenging. In this paper, we investigate prompt-based techniques to guide LLMs in producing outputs compliant with a pre-existing domain-specific controlled natural language called Language for Embedded Safety and Security (LESS). Additionally, we evaluate the effectiveness of LLMs in automating test case generation. Our results show that structured prompt engineering significantly enhances the accuracy and consistency of generated requirements, and that using controlled language formats such as LESS as an intermediate representation substantially improves test case generation accuracy.