Leveraging Large Language Models for Enhanced Process Model Comprehension

arXiv (Cornell University)

Abstract

In Business Process Management (BPM), effectively comprehending process models is crucial yet poses significant challenges, particularly as organizations scale and processes become more complex. This paper introduces a novel framework utilizing the advanced capabilities of Large Language Models (LLMs) to enhance the interpretability of complex process models. We present different methods for abstracting business process models into a format accessible to LLMs, and we implement advanced prompting strategies specifically designed to optimize LLM performance within our framework. Additionally, we present a tool, AIPA, that implements our proposed framework and allows for conversational process querying. We evaluate our framework and tool by i) an automatic evaluation comparing different LLMs, model abstractions, and prompting strategies and ii) a user study designed to assess AIPA's effectiveness comprehensively. Results demonstrate our framework's ability to improve the accessibility and interpretability of process models, pioneering new pathways for integrating AI technologies into the BPM field.

Authors 8

1. Humam Kourani Aachen

   Fraunhofer Institute for Applied Information Technology · RWTH Aachen University

   Affiliation as printed

   Fraunhofer Institute for Applied Information Technology FIT , Schloss Birlinghoven , Sankt Augustin , 53757 , Germany

   RWTH Aachen University , Ahornstraße 55 , Aachen , 52074 , Germany

2. Alessandro Berti Aachen

   Fraunhofer Institute for Applied Information Technology · RWTH Aachen University

   Affiliation as printed

   Fraunhofer Institute for Applied Information Technology FIT , Schloss Birlinghoven , Sankt Augustin , 53757 , Germany

   RWTH Aachen University , Ahornstraße 55 , Aachen , 52074 , Germany

3. Jasmin Hennrich

   Fraunhofer Institute for Applied Information Technology

   Affiliation as printed

   Fraunhofer Institute for Applied Information Technology FIT , Schloss Birlinghoven , Sankt Augustin , 53757 , Germany

4. Wolfgang Kratsch

   Fraunhofer Institute for Applied Information Technology

   Affiliation as printed

   Fraunhofer Institute for Applied Information Technology FIT , Schloss Birlinghoven , Sankt Augustin , 53757 , Germany

5. Robin Weidlich

   Fraunhofer Institute for Applied Information Technology

   Affiliation as printed

   Fraunhofer Institute for Applied Information Technology FIT , Schloss Birlinghoven , Sankt Augustin , 53757 , Germany

6. Chiao-Yun Li Aachen

   Fraunhofer Institute for Applied Information Technology · RWTH Aachen University

   Affiliation as printed

   Fraunhofer Institute for Applied Information Technology FIT , Schloss Birlinghoven , Sankt Augustin , 53757 , Germany

   RWTH Aachen University , Ahornstraße 55 , Aachen , 52074 , Germany

7. Daniel Schuster Aachen

   Fraunhofer Institute for Applied Information Technology · RWTH Aachen University

   Affiliation as printed

   Fraunhofer Institute for Applied Information Technology FIT , Schloss Birlinghoven , Sankt Augustin , 53757 , Germany

   RWTH Aachen University , Ahornstraße 55 , Aachen , 52074 , Germany

8. Wil M. P. van der Aalst Aachen

   Fraunhofer Institute for Applied Information Technology · RWTH Aachen University

   Affiliation as printed

   Fraunhofer Institute for Applied Information Technology FIT , Schloss Birlinghoven , Sankt Augustin , 53757 , Germany

   RWTH Aachen University , Ahornstraße 55 , Aachen , 52074 , Germany