A diagnosis-driven framework detects behavioral inconsistency in LLM-generated BPMN models from ambiguous natural language specs, localizes issues to gateway logic, maps them to source text, and repairs the specifications to reduce variability.
Automated BPMN model generation from textual process descriptions: A multi-stage LLM-driven approach
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Ambiguity Detection and Elimination in Automated Executable Process Modeling
A diagnosis-driven framework detects behavioral inconsistency in LLM-generated BPMN models from ambiguous natural language specs, localizes issues to gateway logic, maps them to source text, and repairs the specifications to reduce variability.