# LLM-Assisted Translation of Legacy FORTRAN Codes to C++: A Cross-Platform Study

arXiv: https://arxiv.org/abs/2504.15424 · HTML: https://mlsanity.com/paper/2504.15424/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 44 references that are in the map.
- First posted on arXiv 21 Apr 2025.

## Builds on (most cited first, 10 of 10)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement](https://mlsanity.com/paper/2402.14658/) (2024)
- [Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine](https://mlsanity.com/paper/2301.08745/) (2023)
- [A Tutorial on Kernel Density Estimation and Recent Advances](https://mlsanity.com/paper/1704.03924/) (2017)
- [CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation](https://mlsanity.com/paper/2310.04951/) (2023)
- [SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts](https://mlsanity.com/paper/2405.07518/) (2024)
- [Enhancing Code Translation in Language Models with Few-Shot Learning via Retrieval-Augmented Generation](https://mlsanity.com/paper/2407.19619/) (2024)
- [Creating a Dataset for High-Performance Computing Code Translation using LLMs: A Bridge Between OpenMP Fortran and C++](https://mlsanity.com/paper/2307.07686/) (2023)

## Built on by (most cited first, 7 of 7)

- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [From Legacy Fortran to Portable Kokkos: An Autonomous Agentic AI Workflow](https://mlsanity.com/paper/2509.12443/) (2025)
- [Leveraging LLMs to Automate Energy-Aware Refactoring of Parallel Scientific Codes](https://mlsanity.com/paper/2505.02184/) (2025)
- [Systematic LLM Translation of Legacy Scientific Code to Differentiable Frameworks: Application to a Land Surface Model](https://mlsanity.com/paper/2606.07681/) (2026)
- [Performance Evaluation of General Purpose Large Language Models for Basic Linear Algebra Subprograms Code Generation](https://mlsanity.com/paper/2507.04697/) (2025)
- [LLM Translation of Compiler Intermediate Representation](https://mlsanity.com/paper/2605.08247/) (2026)
- [An Agentic Workflow for Legacy HPC Modernization: Converting the Two-Electron-Integral Core of GAMESS](https://mlsanity.com/paper/2608.12249/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly being leveraged for generating and translating scientific computer codes by both domain-experts and non-domain experts. Fortran has served as one of the go to programming languages in legacy high-performance computing (HPC) for scientific discoveries. Despite growing adoption, LLM-based code translation of legacy code-bases has not been thoroughly assessed or quantified for its usability. Here, we studied the applicability of LLM-based translation of Fortran to C++ as a step towards building an agentic-workflow using open-weight LLMs on two different computational platforms. We statistically quantified the compilation accuracy of the translated C++ codes, measured the similarity of the LLM translated code to the human translated C++ code, and statistically quantified the output similarity of the Fortran to C++ translation.