Utilizing LLMs for Industrial Process Automation: A Case Study on Modifying RAPID Programs

TL;DR

This paper explores how large language models can be effectively used for industrial process automation by employing few-shot prompting techniques on proprietary, domain-specific languages without extensive model training.

Contribution

It demonstrates that few-shot prompting enables LLMs to handle industrial automation tasks in specialized languages, maintaining data privacy and reducing training efforts.

Findings

Few-shot prompting suffices for simple industrial language tasks

On-premise LLM deployment protects sensitive data

Potential for LLMs to support proprietary industrial languages

Abstract

How to best use Large Language Models (LLMs) for software engineering is covered in many publications in recent years. However, most of this work focuses on widely-used general purpose programming languages. The utility of LLMs for software within the industrial process automation domain, with highly-specialized languages that are typically only used in proprietary contexts, is still underexplored. Within this paper, we study enterprises can achieve on their own without investing large amounts of effort into the training of models specific to the domain-specific languages that are used. We show that few-shot prompting approaches are sufficient to solve simple problems in a language that is otherwise not well-supported by an LLM and that is possible on-premise, thereby ensuring the protection of sensitive company data.