Conversational Process Model Redesign

TL;DR

This paper proposes a conversational approach for process model redesign using LLMs, enabling iterative, explainable, and pattern-based modifications with extensive evaluation.

Contribution

It introduces a multi-step, pattern-aware method for process model redesign with LLMs, emphasizing explainability and user interaction in process management.

Findings

Some change patterns are difficult for LLMs to understand.

Clear user change descriptions are crucial for effective redesign.

A hybrid approach improves pattern application and user interaction.

Abstract

With the recent success of large language models (LLMs), the idea of AI-augmented Business Process Management systems is becoming more feasible. One of their essential characteristics is the ability to be conversationally actionable, allowing humans to interact with the LLM effectively to perform crucial process life cycle tasks such as process model design and redesign. However, most current research focuses on single-prompt execution and evaluation of results, rather than on continuous interaction between the user and the LLM. In this work, we aim to explore the feasibility of using LLMs to empower domain experts in the creation and redesign of process models in an iterative and effective way. The proposed conversational process model redesign (CPMR) approach receives as input a process model and a redesign request by the user in natural language. Instead of just letting the LLM make changes, the LLM is employed to (a) identify process change patterns from literature, (b) re-phrase the change request to be aligned with an expected wording for the identified pattern (i.e., the meaning), and then to (c) apply the meaning of the change to the process model. This multi-step approach allows for explainable and reproducible changes. In order to ensure the feasibility of the CPMR approach, and to find out how well the patterns from literature can be handled by the LLM, we perform an extensive evaluation, also in comparison to a baseline approach without change patterns. The results show that some patterns are hard to understand by LLMs and by users and that clear change descriptions by users are essential. Overall, we recommend a hybrid approach that identifies all used change patterns and then directly applies those patterns that work correctly and for the others derives follow-up questions in order to improve user input.