An empirical study of an LLM critique-refine pipeline for activity diagrams finds algorithmic structural checks beat LLM checks, but measurement design issues cloud the results.
Automating data flow diagram generation from user stories using large language models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
The Impact of Critique on LLM-Based Model Generation from Natural Language: The Case of Activity Diagrams
An empirical study of an LLM critique-refine pipeline for activity diagrams finds algorithmic structural checks beat LLM checks, but measurement design issues cloud the results.