Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jiang, He, Wang, Yufu, Lin, Hao, Zou, Peiyu, Zhou, Zhide, Jia, Ang, Li, Xiaochen, Ren, Zhilei
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2510.09400
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918158223278080
author Jiang, He
Wang, Yufu
Lin, Hao
Zou, Peiyu
Zhou, Zhide
Jia, Ang
Li, Xiaochen
Ren, Zhilei
author_facet Jiang, He
Wang, Yufu
Lin, Hao
Zou, Peiyu
Zhou, Zhide
Jia, Ang
Li, Xiaochen
Ren, Zhilei
contents Large Language Models (LLMs) have shown strong performance in automated source-to-target code translation through pretraining on extensive code corpora. However, mainstream LLM-based code translation methods suffer from two critical limitations. First, they are highly sensitive to language-specific features, which often introduce source-language syntax or lexicon into the output, leading to syntactic confusion. Second, they lack fine-grained semantic alignment due to an over-reliance on function-level parallel datasets, resulting in semantic misalignment between the translated code and the original source. To overcome these limitations, we propose TIT, a Tree-structured Instruction Tuning paradigm for LLM-based code translation. Specifically, TIT consists of three modules. First, to mitigate syntactic confusion, the syntactic information representation module integrates language-agnostic syntactic features via structured parsing. Then, to generate high-quality fine-grained parallel data, the fine-grained parallel dataset augmentation module aligns nodes with code segments through statement-level segmentation and contrastive matching. Finally, we leverage the dual-stage tree instruction tuning module to alleviate the contextual processing burden on the LLM caused by the introduction of syntactic information. The first stage employs syntax-aware fine-tuning to enable the LLM to autonomously comprehend structured syntactic information, while the second stage utilizes code generation fine-tuning to guide the model in generating accurate target code based on function-level syntactic dependencies. The experimental results demonstrate that the proposed method significantly outperforms existing approaches in multiple LLMs, achieving a success rate 1.22x-1.75x higher in code translation while markedly reducing syntactic confusion.
format Preprint
id arxiv_https___arxiv_org_abs_2510_09400
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TIT: A Tree-Structured Instruction Tuning Approach for LLM-Based Code Translation
Jiang, He
Wang, Yufu
Lin, Hao
Zou, Peiyu
Zhou, Zhide
Jia, Ang
Li, Xiaochen
Ren, Zhilei
Software Engineering
Large Language Models (LLMs) have shown strong performance in automated source-to-target code translation through pretraining on extensive code corpora. However, mainstream LLM-based code translation methods suffer from two critical limitations. First, they are highly sensitive to language-specific features, which often introduce source-language syntax or lexicon into the output, leading to syntactic confusion. Second, they lack fine-grained semantic alignment due to an over-reliance on function-level parallel datasets, resulting in semantic misalignment between the translated code and the original source. To overcome these limitations, we propose TIT, a Tree-structured Instruction Tuning paradigm for LLM-based code translation. Specifically, TIT consists of three modules. First, to mitigate syntactic confusion, the syntactic information representation module integrates language-agnostic syntactic features via structured parsing. Then, to generate high-quality fine-grained parallel data, the fine-grained parallel dataset augmentation module aligns nodes with code segments through statement-level segmentation and contrastive matching. Finally, we leverage the dual-stage tree instruction tuning module to alleviate the contextual processing burden on the LLM caused by the introduction of syntactic information. The first stage employs syntax-aware fine-tuning to enable the LLM to autonomously comprehend structured syntactic information, while the second stage utilizes code generation fine-tuning to guide the model in generating accurate target code based on function-level syntactic dependencies. The experimental results demonstrate that the proposed method significantly outperforms existing approaches in multiple LLMs, achieving a success rate 1.22x-1.75x higher in code translation while markedly reducing syntactic confusion.
title TIT: A Tree-Structured Instruction Tuning Approach for LLM-Based Code Translation
topic Software Engineering
url https://arxiv.org/abs/2510.09400