Can Programming Languages Boost Each Other via Instruction Tuning?
share
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 trained on the HTML corpus can improve Java by an absolute 15.24 training data is released at https://github.com/NL2Code/CodeM.
READ FULL TEXT