Automatic Instantiation of Assurance Cases from Patterns using Large Language Models

Justifying the correct implementation of mission-critical systems' non-functional requirements (e.g., safety, and security) is crucial to prevent system failure. The latter could have severe consequences such as the death of people and financial losses. Assurance cases can be used to prevent system failure. They are structured sets of arguments supported by evidence, demonstrating that a system’s non-functional requirements have been correctly implemented. Assurance case patterns serve as templates derived from previous successful assurance cases, aimed at facilitating the creation of new assurance cases. Despite the use of these patterns to generate assurance cases, their instantiation remains a largely manual and error-prone process that heavily relies on domain expertise. Thus, exploring techniques to support their automatic instantiation becomes crucial. To address this, our thesis explores the literature on assurance case patterns to understand recent advancements and trends characterizing that literature. Then we investigated the potential of Large Language Models (LLMs) in automating the generation of assurance cases that comply with specific assurance case patterns. Our findings suggest that LLMs can generate assurance cases that comply with the given patterns. However, this study also highlights that LLMs may struggle with understanding some nuances related to pattern-specific relationships. While LLMs exhibit potential in the automatic generation of assurance cases, their capabilities still fall short compared to human experts. Therefore, a semi-automatic approach to instantiating assurance cases may be more advisable at this time.