1. Can Programming Languages Boost Each Other via Instruction Tuning?
- Author
-
Zan, Daoguang, Yu, Ailun, Shen, Bo, Zhang, Jiaxin, Chen, Taihong, Geng, Bing, Chen, Bei, Ji, Jichuan, Yao, Yafen, Wang, Yongji, and Wang, Qianxiang
- Subjects
Computer Science - Computation and Language ,Computer Science - Artificial Intelligence ,Computer Science - Programming Languages ,Computer Science - Software Engineering - Abstract
When human programmers have mastered a programming language, it would be easier when they learn a new programming language. In this report, we focus on exploring whether programming languages can boost each other during the instruction fine-tuning phase of code large language models. We conduct extensive experiments of 8 popular programming languages (Python, JavaScript, TypeScript, C, C++, Java, Go, HTML) on StarCoder. Results demonstrate that programming languages can significantly improve each other. For example, CodeM-Python 15B trained on Python is able to increase Java by an absolute 17.95% pass@1 on HumanEval-X. More surprisingly, we found that CodeM-HTML 7B trained on the HTML corpus can improve Java by an absolute 15.24% pass@1. Our training data is released at https://github.com/NL2Code/CodeM., Comment: Work in progress
- Published
- 2023