← Search

Yuanliang Zhang

1 accepted papers

2024

At Which Training Stage Does Code Data Help LLMs Reasoning?

ICLR 2024spotlight

Large Language models (LLMs) have exhibited remarkable reasoning capabilities and become the foundation of language technologies. Inspired by the great success of code data in training LLMs, we naturally wonder at which training stage introducing code data can really help LLMs reasoning. To this end…