Leveraging The Performance of Large Language Models in Systems Engineering Applications

Abstract

The integration of Artificial Intelligence in systems engineering marks a significant evolutionary step in managing complex projects. Artificial Intelligence can optimize system designs and processes, leading to cost savings and efficiency improvements. One of the most groundbreaking advancements is the rise of Foundation Models and the Large Language Models, a recent innovation in Artificial Intelligence. These models represent a new approach where a single model is trained on a massive, diverse corpus of data to handle multiple tasks. This document investigates the use of Large Language Models within systems engineering, the study employs a Retrieval-Augmented Generation framework to address the complexities of specialized engineering tasks effectively. We outline a structured approach to enhance retrieval effectiveness and Leveraging large language model. This approach enables us to reduce the error rate in systems engineering prediction of different Large Language Models by 33.33%. Our innovative setup paves the way for the future Systems Engineering tool uses unique enhanced data corpus, laying on efficient and controlled real time expert knowledge sharing.