Generic filters
Exact matches only
Search in title
Search in excerpt
Search in content
FS Logoi

From data to design

LLM-enabled information extraction across industries


Publikationsform: Fachartikel
Artikelnummer: 03654_2024_06-07_03
Zeitschrift: From data to design
Erscheinungsdatum: 28.06.2024
Autor: Robert Becker, Laura Steffny, Thomas Bleistein, Dirk Werth,
Verlag: Vulkan-Verlag GmbH
Seiten: 9
Publikationsformat: PDF
Sprache: Deutsch


This paper explores the application of Large Language Models (LLMs) in the automotive and supplier industries, with a particular focus on the use of retrieval-augmented generation (RAG) systems to streamline information retrieval from technical documentation. The research, part of the CoLab4DigiTwin project, investigates how digital twins supported by smart services can enhance interdisciplinary collaboration and reduce the reliance on manual data searches. We developed a pipeline utilizing a RAG architecture which uses a vector database for efficient data management and fast access to relevant information, eliminating the need for expensive computational resources. The performance of various open-source LLMs, which are finetuned on German, was evaluated, focusing on readability, clarity, and accuracy. The results show decent performance of the system without the need for model fine-tuning. Future research will aim to refine these processes and extend the applicability of RAG systems, highlighting the potential of Large Language Models to transform industrial data interaction.

Preis: 4,90 €Zum Shop

Infos zum Autor/Verfasser/Herausgeber

Publikationen zum selben Thema