Requirements-driven Slicing of Simulink Models Using LLMs

TL;DR

This paper introduces a novel method leveraging large language models to extract relevant model slices from Simulink models based on specific requirements, enhancing model analysis and impact assessment.

Contribution

It presents a new approach that converts Simulink models into textual form and uses LLMs to identify relevant blocks, improving slicing accuracy and understanding of model requirements.

Findings

Prompts with syntax and semantics yield more accurate slices.

Chain-of-thought and zero-shot prompting strategies improve slice accuracy.

Different textual granularities impact the effectiveness of the slicing process.

Abstract

Model slicing is a useful technique for identifying a subset of a larger model that is relevant to fulfilling a given requirement. Notable applications of slicing include reducing inspection effort when checking design adequacy to meet requirements of interest and when conducting change impact analysis. In this paper, we present a method based on large language models (LLMs) for extracting model slices from graphical Simulink models. Our approach converts a Simulink model into a textual representation, uses an LLM to identify the necessary Simulink blocks for satisfying a specific requirement, and constructs a sound model slice that incorporates the blocks identified by the LLM. We explore how different levels of granularity (verbosity) in transforming Simulink models into textual representations, as well as the strategy used to prompt the LLM, impact the accuracy of the generated slices. Our preliminary findings suggest that prompts created by textual representations that retain the syntax and semantics of Simulink blocks while omitting visual rendering information of Simulink models yield the most accurate slices. Furthermore, the chain-of-thought and zero-shot prompting strategies result in the largest number of accurate model slices produced by our approach.