Just Tell Me: Prompt Engineering in Business Process Management

TL;DR

This paper advocates for using prompt engineering with pre-trained language models to enhance business process management research, avoiding the need for extensive fine-tuning and training data.

Contribution

It develops a research agenda highlighting potentials and challenges of applying prompt engineering in BPM, promoting a shift from fine-tuning to prompt-based methods.

Findings

Prompt engineering can leverage pre-trained LMs for BPM tasks.

It reduces the need for large training datasets.

Identifies key challenges and opportunities in BPM applications.

Abstract

GPT-3 and several other language models (LMs) can effectively address various natural language processing (NLP) tasks, including machine translation and text summarization. Recently, they have also been successfully employed in the business process management (BPM) domain, e.g., for predictive process monitoring and process extraction from text. This, however, typically requires fine-tuning the employed LM, which, among others, necessitates large amounts of suitable training data. A possible solution to this problem is the use of prompt engineering, which leverages pre-trained LMs without fine-tuning them. Recognizing this, we argue that prompt engineering can help bring the capabilities of LMs to BPM research. We use this position paper to develop a research agenda for the use of prompt engineering for BPM research by identifying the associated potentials and challenges.