Print Email Facebook Twitter Knowledge sharing in manufacturing using LLM-powered tools Title Knowledge sharing in manufacturing using LLM-powered tools: User study and model benchmarking Author Kernan Freire, S. (TU Delft Internet of Things) Wang, C.W. (TU Delft Human-Centred Artificial Intelligence) Foosherian, Mina (BIBA – Bremer Institut für Produktion und Logistik GmbH) Wellsandt, Stefan (BIBA - Bremer Institut für Produktion und Logistik GmbH) Ruiz-Arenas, Santiago (Universidad EAFIT) Niforatos, E. (TU Delft Internet of Things) Date 2024 Abstract Recent advances in natural language processing enable more intelligent ways to support knowledge sharing in factories. In manufacturing, operating production lines has become increasingly knowledge-intensive, putting strain on a factory's capacity to train and support new operators. This paper introduces a Large Language Model (LLM)-based system designed to retrieve information from the extensive knowledge contained in factory documentation and knowledge shared by expert operators. The system aims to efficiently answer queries from operators and facilitate the sharing of new knowledge. We conducted a user study at a factory to assess its potential impact and adoption, eliciting several perceived benefits, namely, enabling quicker information retrieval and more efficient resolution of issues. However, the study also highlighted a preference for learning from a human expert when such an option is available. Furthermore, we benchmarked several commercial and open-sourced LLMs for this system. The current state-of-the-art model, GPT-4, consistently outperformed its counterparts, with open-source models trailing closely, presenting an attractive option given their data privacy and customization benefits. In summary, this work offers preliminary insights and a system design for factories considering using LLM tools for knowledge management. Subject natural language interfacebenchmarkingLarge Language Modelsfactoryindustrial settingsindustry 5.0knowledge sharinginformation retrieval To reference this document use: http://resolver.tudelft.nl/uuid:55e2a151-79c6-4c7b-9c67-adbde9d52773 DOI https://doi.org/10.3389/frai.2024.1293084 ISSN 2624-8212 Source Frontiers in Artificial Intelligence, 7 Part of collection Institutional Repository Document type journal article Rights © 2024 S. Kernan Freire, C.W. Wang, Mina Foosherian, Stefan Wellsandt, Santiago Ruiz-Arenas, E. Niforatos Files PDF frai-07-1293084.pdf 804.84 KB Close viewer /islandora/object/uuid:55e2a151-79c6-4c7b-9c67-adbde9d52773/datastream/OBJ/view