Pith. sign in

REVIEW

Can Programming Languages Boost Each Other via Instruction Tuning?

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2308.16824 v2 pith:SJ7RMP3O submitted 2023-08-31 cs.CL cs.AIcs.PLcs.SE

Daoguang Zan , Ailun Yu , Bo Shen , Jiaxin Zhang , Taihong Chen , Bing Geng , Bei Chen , Jichuan Ji
show 3 more authors
Yafen Yao Yongji Wang Qianxiang Wang
This is my paper
classification cs.CLcs.AIcs.PLcs.SE
keywords programminglanguagesjavalanguageotherabsoluteboosthtml
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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.

Discussion (0). Sign in to comment.

Pith tools