2 comments

[ 2.7 ms ] story [ 17.1 ms ] thread
Answering the question: "what is the impact of code data used in pre-training on a large variety of downstream tasks beyond code generation?"
From the abstract: "Across settings, we find a consistent results that code is a critical building block for generalization far beyond coding tasks and improvements to code quality have an outsized impact across all tasks. In particular, compared to text-only pre-training, the addition of code results in up to relative increase of 8.2% in natural language (NL) reasoning, 4.2% in world knowledge, 6.6% improvement in generative win-rates, and a 12x boost in code performance respectively. Our work suggests investments in code quality and preserving code during pre-training have positive impacts."