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 what enterprises can achieve on their own without investing large amounts of effort into the training of models on the domain-specific languages that are used. We show that few-shot prompting approaches are sufficient to solve simple but recurring problems in ABB’s RAPID language even though the language is not well-supported by current LLMs. To ensure correctness, we introduce a custom validator that assesses the structural validity of generated solutions and their adherence to the proprietary standards. Our results show that lightweight, on-premise approaches can provide practical value while preserving sensitive industrial data.
Paper
References (21)
Scroll for more · 9 remaining