Leveraging Generative AI for Extracting Process Models from Multimodal Documents

TL;DR

This paper explores the use of Generative Pre-trained Transformers (GPTs) to automatically generate graphical process models from combined text and image inputs, providing a new dataset and evaluation framework.

Contribution

It introduces a novel multi-modal dataset, evaluation metrics, and open-source code for assessing GPTs in process model generation from multimodal data.

Findings

GPTs show potential for semi-automated process modeling

Evaluation metrics enable systematic assessment

Open-source tools facilitate future research

Abstract

This paper presents an investigation of the capabilities of Generative Pre-trained Transformers (GPTs) to auto-generate graphical process models from multi-modal (i.e., text- and image-based) inputs. More precisely, we first introduce a small dataset as well as a set of evaluation metrics that allow for a ground truth-based evaluation of multi-modal process model generation capabilities. We then conduct an initial evaluation of commercial GPT capabilities using zero-, one-, and few-shot prompting strategies. Our results indicate that GPTs can be useful tools for semi-automated process modeling based on multi-modal inputs. More importantly, the dataset and evaluation metrics as well as the open-source evaluation code provide a structured framework for continued systematic evaluations moving forward.