Conversational Process Model Redesign

2025-05-08

AI Summary

Large language models (LLMs) exhibit limitations in business process model redesign—namely, single-turn prompting, lack of iterative human-in-the-loop interaction, and insufficient interpretability. Method: We propose the first multi-turn, dialogue-based redesign framework grounded in change-pattern recognition and semantic reformulation. Integrating BPMN modeling, natural language understanding, pattern matching, and semantic alignment, it enables domain experts to issue iterative natural-language change requests and executes interpretable, reproducible process reconstruction via three sequential phases: pattern recognition, semantic alignment, and model transformation. Contribution/Results: Empirical evaluation demonstrates that LLMs achieve high accuracy on completeness and correctness metrics for most change types; however, certain patterns expose semantic comprehension bottlenecks, underscoring the necessity of explicit requirement clarification mechanisms. This work establishes a novel paradigm for LLM-augmented, human–AI collaborative process governance.

Technology Category

• Natural Language Processing: (Large) Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production 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.

Problem

• Enabling conversational AI for iterative process model redesign
• Improving LLM interaction for explainable process changes
• Evaluating LLM performance in handling process change patterns

Innovation

• LLM-augmented conversational process redesign
• Multi-step pattern identification and application
• Explainable and reproducible process model changes