Proceedings

Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization

Yuhan Wu, Huan Zhang, Wei Cheng, Chen Shen, Jingyue Yang, Wei Hu

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 5973-5981.

https://doi.org/10.24963/ijcai.2026/665

Keywords

  • Natural Language Processing: Machine translation and multilinguality
  • Natural Language Processing: Applications

Abstract

LLMs have shown immense potential for code translation, yet they often struggle to ensure both syntactic correctness and semantic consistency. While preference-based learning offers a promising alignment strategy, it is hindered by unreliable semantic rewards derived from sparse test cases or restrictive reference translations. We argue that a robust semantic reward for code translation must be derived directly from the source code. In this paper, we propose CTO to improve code translation with syntax-guided and semantic-aware preference optimization.

Through contrastive learning, we train a cross-lingual semantic model to directly assess functional equivalence between source and translated code. By formulating code translation as a multi-objective optimization problem, this robust semantic signal is seamlessly unified with compiler-based syntactic feedback within the direct preference optimization framework. Extensive experiments on C++, Java, and Python translations demonstrate that CTO significantly outperforms existing baselines and alternative preference optimization strategies.

Yuhan Wu, Huan Zhang, Wei Cheng, Chen Shen, Jingyue Yang, and Wei Hu. 2026. Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 5973–5981. https://doi.org/10.24963/ijcai.2026/665
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards