Conversational Process Model Redesign

TL;DR

The paper explores using large language models to support domain experts in iterative BPMN diagram redesign via conversational process redesign (CPD). It formalizes a three-step identify-derive-apply pipeline that maps natural-language redesign requests to change patterns drawn from Weber et al., aiming for explainable and reproducible edits. An extensive evaluation with 64 participants across three LLMs reveals that several patterns are reliably handled, while others suffer from interpretation or application gaps, highlighting the need for better prompts, pattern clarification, and potentially hybrid approaches. The work demonstrates the feasibility of AI-augmented, multi-turn BPMN redesign and outlines directions for expanding pattern sets, formalizing meanings, and integrating user-behavior insights for more robust CPD systems.

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 (CPD) 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 CPD approach, and to find out how well the patterns from literature can be handled by the LLM, we performed an extensive evaluation. The results show that some patterns are hard to understand by LLMs and by users. Within the scope of the study, we demonstrated that users need support to describe the changes clearly. Overall the evaluation shows that the LLMs can handle most changes well according to a set of completeness and correctness criteria.

Figures (4)

• Figure 1: Conversational process modeling including conversational process model redesign
• Figure 2: Overview on LLM-based Process Model Redesign.
• Figure 3: User survey. Example
• Figure 4: Evaluation Procedure