A locally deployable LLM pipeline with documentation-based ranking and iterative classification extracts domain models from Java code, achieving an F1 of 0.90 for classes but with evaluation caveats.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Automated Domain Model Extraction from Source Code using Heuristics and Open-Source LLMs
A locally deployable LLM pipeline with documentation-based ranking and iterative classification extracts domain models from Java code, achieving an F1 of 0.90 for classes but with evaluation caveats.