Adopting RAG for LLM-Aided Future Vehicle Design

TL;DR

This paper investigates integrating Retrieval-Augmented Generation with Large Language Models to improve automotive design automation, demonstrating promising results with multiple models and addressing data privacy concerns.

Contribution

It introduces the application of RAG-augmented LLMs in automotive design, including case studies and performance comparisons of different models.

Findings

GPT-4 achieves highest accuracy and speed.

LLAMA3 and Mistral are viable for local deployment.

RAG enhances context-aware responses in automotive tasks.

Abstract

In this paper, we explore the integration of Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) to enhance automated design and software development in the automotive industry. We present two case studies: a standardization compliance chatbot and a design copilot, both utilizing RAG to provide accurate, context-aware responses. We evaluate four LLMs-GPT-4o, LLAMA3, Mistral, and Mixtral -- comparing their answering accuracy and execution time. Our results demonstrate that while GPT-4 offers superior performance, LLAMA3 and Mistral also show promising capabilities for local deployment, addressing data privacy concerns in automotive applications. This study highlights the potential of RAG-augmented LLMs in improving design workflows and compliance in automotive engineering.