Architecture-Centric Code Migration for Legacy Industrial Systems Using LLMs
TL;DR
This research focuses on Maven configuration and structure updates and explores how the CodeT5 model can automate the migration of Java 8 projects to Java 17, finding the model accelerates parts of migration but remains unsuitable for fully automated use.
Abstract
: This research focuses on Maven configuration and structure updates and explores how the CodeT5 model can automate the migration of Java 8 projects to Java 17. Manually migrating large Java applications is a tedious and error-prone task that requires significant developer time and attention. To create a high-quality training dataset, Java 8 projects are collected from GitHub and manually converted to Java 17 using large-scale modern language models such as ChatGPT and Claude. Each repository is migrated module-by-module to ensure structural and functional accuracy. This process has created a parallel dataset of approximately 100 repositories, formatted as a JSONL file to allow efficient fine-tuning of small CodeT5 models. The model fine-tuning is evaluated using standard metrics, including BLEU, ROUGE, and BERTScore. The results show strong semantic agreement between the generated and reference outputs, with a BERTScore F1 of 0.982 and token precision of 0.9990. The model accelerates parts of migration but remains unsuitable for fully automated use due to truncated outputs and incomplete Java file structures, with an average output-length ratio of 0.8 and an accuracy of 62% for the Java version.