Harnessing Large Language Models for Cognitive Assistants in Factories

Conference Paper (2023)
Author(s)

S. Kernan Freire (TU Delft - Internet of Things)

Mina Foosherian (University of Bremen)

C.W. Wang (TU Delft - Human-Centred Artificial Intelligence)

Evangelos Niforatos (TU Delft - Internet of Things)

Research Group
Human-Centred Artificial Intelligence
Copyright
© 2023 S. Kernan Freire, Mina Foosherian, C.W. Wang, E. Niforatos
DOI related publication
https://doi.org/10.1145/3571884.3604313
More Info
expand_more
Publication Year
2023
Language
English
Copyright
© 2023 S. Kernan Freire, Mina Foosherian, C.W. Wang, E. Niforatos
Research Group
Human-Centred Artificial Intelligence
ISBN (electronic)
979-8-4007-0014-9
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

As agile manufacturing expands and workforce mobility increases, the importance of efficient knowledge transfer among factory workers grows. Cognitive Assistants (CAs) with Large Language Models (LLMs), like GPT-3.5, can bridge knowledge gaps and improve worker performance in manufacturing settings. This study investigates the opportunities, risks, and user acceptance of LLM-powered CAs in two factory contexts: textile and detergent production. Several opportunities and risks are identified through a literature review, proof-of-concept implementation, and focus group sessions. Factory representatives raise concerns regarding data security, privacy, and the reliability of LLMs in high-stake environments. By following design guidelines regarding persistent memory, real-time data integration, security, privacy, and ethical concerns, LLM-powered CAs can become valuable assets in manufacturing settings and other industries.

Files

3571884.3604313.pdf
(pdf | 0.844 Mb)
- Embargo expired in 19-01-2024
License info not available