Development and Evaluation of a Retrieval-Augmented Generation Tool for Creating SAPPhIRE Models of Artificial Systems

TL;DR

This paper introduces a Retrieval-Augmented Generation tool that leverages Large Language Models to automate the creation of SAPPhIRE causality models of artificial systems, aiming to reduce manual effort and improve accuracy.

Contribution

It presents a novel RAG-based approach for generating SAPPhIRE models and provides an initial evaluation of its effectiveness in terms of factual accuracy and reliability.

Findings

The RAG tool can generate SAPPhIRE constructs with promising accuracy.

Preliminary evaluation shows improved efficiency over manual modeling.

The approach demonstrates potential for automating complex system representations.

Abstract

Representing systems using the SAPPhIRE causality model is found useful in supporting design-by-analogy. However, creating a SAPPhIRE model of artificial or biological systems is an effort-intensive process that requires human experts to source technical knowledge from multiple technical documents regarding how the system works. This research investigates how to leverage Large Language Models (LLMs) in creating structured descriptions of systems using the SAPPhIRE model of causality. This paper, the second part of the two-part research, presents a new Retrieval-Augmented Generation (RAG) tool for generating information related to SAPPhIRE constructs of artificial systems and reports the results from a preliminary evaluation of the tool's success - focusing on the factual accuracy and reliability of outcomes.