Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kumar, Jahnavi, Janapati, Venkata Lakshmana Sasaank, Tanguturi, Mokshith Reddy, Chimalakonda, Sridhar
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2501.05724
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916561011343360
author Kumar, Jahnavi
Janapati, Venkata Lakshmana Sasaank
Tanguturi, Mokshith Reddy
Chimalakonda, Sridhar
author_facet Kumar, Jahnavi
Janapati, Venkata Lakshmana Sasaank
Tanguturi, Mokshith Reddy
Chimalakonda, Sridhar
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_05724
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle I Can't Share Code, but I need Translation -- An Empirical Study on Code Translation through Federated LLM
Kumar, Jahnavi
Janapati, Venkata Lakshmana Sasaank
Tanguturi, Mokshith Reddy
Chimalakonda, Sridhar
Software Engineering
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.
title I Can't Share Code, but I need Translation -- An Empirical Study on Code Translation through Federated LLM
topic Software Engineering
url https://arxiv.org/abs/2501.05724