Ambiguity Detection and Elimination in Automated Executable Process Modeling

TL;DR

This paper introduces a framework to detect, localize, and repair ambiguities in natural-language specifications used for generating executable BPMN process models, ensuring more stable and consistent behavior.

Contribution

It presents a diagnosis-driven, closed-loop method that refines natural-language inputs to improve the stability of automatically generated process models.

Findings

Reduces variability in regenerated model behavior.

Effectively localizes divergence to specific gateway logic.

Maps divergence back to narrative segments for targeted repair.

Abstract

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.