I Can't Share Code, but I need Translation -- An Empirical Study on Code Translation through Federated LLM

TL;DR

This paper presents an empirical study on federated learning for code translation using large language models, demonstrating improved translation accuracy while preserving data privacy.

Contribution

It introduces a novel federated LLM approach for code translation, enabling collaborative training without sharing sensitive code data.

Findings

Over 40% improvement in CodeBLEU score with FedLLM

Effective translation between C# and Java

Federated approach preserves data privacy while enhancing performance

Abstract

Owing to the rapid evolution of technologies and project requirements, organizations need to upgrade the code base in their software projects to a new version of the programming language or even translating to an entirely new one. However, code translation is resource-intensive and requires expertise in both the source and target languages. While researchers have made progress in automating translations between legacy and modern languages, recent work has increasingly turned to pre-trained Large Language Models (LLMs) to translate efficiently. Given the proprietary nature of code, organizations prefer fine-tuning LLMs locally rather than relying on external APIs. This is one of the first empirical studies that proposes a Federated LLM-based approach for code translation. The proposed approach enables clients to jointly train a code translator without sharing sensitive data. This study demonstrates that participants can collaboratively develop a FedLLM for efficient code translation (particularly C\# to Java and vice-versa) with superior results (more than 40\% improvement in CodeLLaMA's CodeBLEU score) compared to individual client models. Our findings indicate that FedLLM offers a collaborative approach to code translation and could serve as a promising direction for future research in this field.