Generative Artificial Intelligence for Intent-based Industrial Automation

Fine-tuning to adapt pre-trained language models to specific tasks is important in intent-based industrial automation systems that can create models that are more suitable for specific domains, such as industrial automation services, making them more useful in real-world applications. This paper presents an application of such a platform for understanding and applying fine-tuning using the different pre-trained LLM models. Our evaluations have shown that the fine-tuning process can lead to a substantial improvement for pretrained LLMs. Finally, such integration of generative AI into intent-based industrial automation can bring various benefits that improve manufacturing processes\u2019 overall efficiency, responsiveness, quality and cost-effectiveness. ACKNOWLEDGMENTS This work has been partially supported by the Spanish Ministry of Economy and Competitiveness (MINECO\u2014Program UNICO I+D under Grant TSI-063000-2021-54, Grant TSI-063000-2021-55, \u201CERDF A way of making Europe\u201D project funded by MCIN/AEI/ 10.13039/501100011033 under grant PID2021-126431OB-I00 and Generalitat de Catalunya grant 2021 SGR 00770, and by the Science Foundation Ireland under the CONNECT phase 2 (Grant no. 13/RC/2077 P2) project. REFERENCES