The paper introduces a dialogue-based fine-tuning dataset for Fortran-to-C++ translation and reports up to 3.31x CodeBLEU improvement and up to 92 percent compilation success on fine-tuned LLMs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fortran2CPP: Automating Fortran-to-C++ Translation using LLMs via Multi-Turn Dialogue and Dual-Agent Integration
The paper introduces a dialogue-based fine-tuning dataset for Fortran-to-C++ translation and reports up to 3.31x CodeBLEU improvement and up to 92 percent compilation success on fine-tuned LLMs.