Using Large Language Models for Ethical Process Modeling: A Case Study

In this paper, we explore the potential of Large Language Models (LLMs) to facilitate and assist a human designer in creating ethical process models within organizational contexts. Our study starts from a simple case study related to the recruitment scenario, where we first develop and test the use of LLMs to design process flow diagrams and then identify potential sources of unfairness. The LLMs contribute to assisting designers in ethically reengineering the process models. The results are used to create a classification of potential unfairness sources and corresponding impact on processes, useful to propose refinements of process models, whenever it is possible. Our research represents the first practical application of LLMs for ethical process modeling in real-world scenarios.