Ambiguity Detection and Elimination in Automated Executable Process Modeling
For practitioners using LLMs to generate executable process models, this framework provides a method to detect and repair ambiguous specifications without ground-truth models.
The paper presents a framework that detects behavioral inconsistency in automatically generated BPMN models from natural-language specifications, localizes divergence to gateway logic, and repairs the source text. Experiments on health-guidance policies show reduced variability in regenerated model behavior.
Automated generation of executable Business Process Model and Notation (BPMN) models from natural-language specifications is increasingly enabled by large language models. However, ambiguous or underspecified text can yield structurally valid models with different simulated behavior. Our goal is not to prove that one generated BPMN model is semantically correct, but to detect when a natural-language specification fails to support a stable executable interpretation under repeated generation and simulation. We present a diagnosis-driven framework that detects behavioral inconsistency from the empirical distribution of key performance indicators (KPIs), localizes divergence to gateway logic using model-based diagnosis, maps that logic back to verbatim narrative segments, and repairs the source text through evidence-based refinement. Experiments on diabetic nephropathy health-guidance policies show that the method reduces variability in regenerated model behavior. The result is a closed-loop approach for validating and repairing executable process specifications in the absence of ground-truth BPMN models.