Integrating Domain Knowledge into Process Discovery Using Large Language Models
This work addresses the reliability issue in process discovery for operational analysis and improvement by incorporating expert knowledge, though it is incremental as it builds on existing methods like IMr with LLM enhancements.
The authors tackled the problem of inaccurate process models derived from incomplete or noisy event logs by integrating domain knowledge expressed in natural language using Large Language Models (LLMs) to extract declarative rules, resulting in a framework that guides process discovery to avoid problematic structures and was evaluated with domain experts in a real-life case study.
Process discovery aims to derive process models from event logs, providing insights into operational behavior and forming a foundation for conformance checking and process improvement. However, models derived solely from event data may not accurately reflect the real process, as event logs are often incomplete or affected by noise, and domain knowledge, an important complementary resource, is typically disregarded. As a result, the discovered models may lack reliability for downstream tasks. We propose an interactive framework that incorporates domain knowledge, expressed in natural language, into the process discovery pipeline using Large Language Models (LLMs). Our approach leverages LLMs to extract declarative rules from textual descriptions provided by domain experts. These rules are used to guide the IMr discovery algorithm, which recursively constructs process models by combining insights from both the event log and the extracted rules, helping to avoid problematic process structures that contradict domain knowledge. The framework coordinates interactions among the LLM, domain experts, and a set of backend services. We present a fully implemented tool that supports this workflow and conduct an extensive evaluation of multiple LLMs and prompt engineering strategies. Our empirical study includes a case study based on a real-life event log with the involvement of domain experts, who assessed the usability and effectiveness of the framework.