AST-guided fine-tuning of T5 models improves SVRF/DRC code generation accuracy on a private 741-example benchmark, with the best model reaching 62.9% on a custom AST-weighted metric.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
An AST-guided LLM Approach for SVRF Code Synthesis
AST-guided fine-tuning of T5 models improves SVRF/DRC code generation accuracy on a private 741-example benchmark, with the best model reaching 62.9% on a custom AST-weighted metric.