INTERTRANS: Leveraging Transitive Intermediate Translations to Enhance LLM-Based Code Translation

• Published in: Proceedings / International Conference on Software Engineering pp. 1153 - 1164
• Main Authors: Macedo, Marcos, Tian, Yuan, Nie, Pengyu, Cogo, Filipe R., Adams, Bram
• Format: Conference Proceeding
• Language: English
• Published: IEEE 26.04.2025
• Subjects: Accuracy; automated code translation; Benchmark testing; Codes; Computer languages; intermediate representation; Large language models; LLM; Multilingual; Semantics; Software engineering; Syntactics; Translation; tree of code translation
• ISSN: 1558-1225
• DOI: 10.1109/ICSE55347.2025.00236

Code translation aims to convert a program from one programming language (PL) to another. This long-standing software engineering task is crucial for modernizing legacy systems, ensuring cross-platform compatibility, enhancing performance, and more. However, automating this process remains challenging due to many syntactic and semantic differences between PLs. Recent studies show that even advanced techniques such as large language models (LLMs), especially open-source LLMs, still struggle with the task. Currently, code LLMs are trained with source code from multiple programming languages, thus presenting multilingual capabilities. In this paper, we investigate whether such capabilities can be harnessed to enhance code translation. To achieve this goal, we introduce INTERTRANS, an LLM-based automated code translation approach that, in contrast to existing approaches, leverages intermediate translations to bridge the syntactic and semantic gaps between source and target PLs. INTERTRANS contains two stages. It first utilizes a novel Tree of Code Translation (ToCT) algorithm to plan transitive intermediate translation sequences between a given source and target PL, then validates them in a specific order. We evaluate INTERTRANS with three open LLMs on three benchmarks (i.e., CodeNet, HumanEval-X, and TransCoder) involving six PLs. Results show an absolute improvement of 18.3% to 43.3% in Computation Accuracy (CA) for INTERTRANS over Direct Translation with 10 attempts. The best-performing variant of INTERTRANS (with the Magicoder LLM) achieved an average CA of 87.3%-95.4% on three benchmarks.