Adopting RAG for LLM-Aided Future Vehicle Design

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zolfaghari, Vahid, Petrovic, Nenad, Pan, Fengjunjie, Lebioda, Krzysztof, Knoll, Alois
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929591709335552
author Zolfaghari, Vahid
Petrovic, Nenad
Pan, Fengjunjie
Lebioda, Krzysztof
Knoll, Alois
author_facet Zolfaghari, Vahid
Petrovic, Nenad
Pan, Fengjunjie
Lebioda, Krzysztof
Knoll, Alois
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_09590
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adopting RAG for LLM-Aided Future Vehicle Design
Zolfaghari, Vahid
Petrovic, Nenad
Pan, Fengjunjie
Lebioda, Krzysztof
Knoll, Alois
Software Engineering
Artificial Intelligence
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.
title Adopting RAG for LLM-Aided Future Vehicle Design
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2411.09590