1 code implementation • 23 Apr 2024 • Zhen Yang, Fang Liu, Zhongxing Yu, Jacky Wai Keung, Jia Li, Shuo Liu, Yifan Hong, Xiaoxue Ma, Zhi Jin, Ge Li
This paper investigates diverse LLMs and learning-based transpilers for automated code translation tasks, finding that: although certain LLMs have outperformed current transpilers, they still have some accuracy issues, where most of the failures are induced by a lack of comprehension of source programs, missing clear instructions on I/O types in translation, and ignoring discrepancies between source and target programs.
1 code implementation • 22 Jul 2019 • Zhongxing Yu, Matias Martinez, Zimin Chen, Tegawendé F. Bissyandé, Martin Monperrus
We instantiate our approach in the context of repair transform prediction for Java programs.
2 code implementations • 25 Oct 2017 • Thomas Durieux, Youssef Hamadi, Zhongxing Yu, Benoit Baudry, Martin Monperrus
In this paper, we study, design and perform an experiment that analyzes the size and the diversity of the failure-oblivious behaviors.
Software Engineering