However, said Agrawal, while it’s relatively easy to evaluate models on math or coding tasks, “assessing models in subjective areas such as reasoning is much more challenging.

NFT is a pure supervised learning method for improving LLMs' math-reasoning abilities with no external teachers. As an SL method, NFT outperforms leading RL algorithms like GRPO and DAPO in 7B model ...

Explore a wide range of recent research in mathematics. From mathematical modeling to why some people have difficulty learning math, read all the math-related news here.

Add a description, image, and links to the eval-library topic page so that developers can more easily learn about it ...