Paper Image

Enabling LLMs to solve math problems with code

Published on:

5 October 2023

Primary Category:

Computation and Language

Paper Authors:

Ke Wang,

Houxing Ren,

Aojun Zhou,

Zimu Lu,

Sichun Luo,

Weikang Shi,

Renrui Zhang,

Linqi Song,

Mingjie Zhan,

Hongsheng Li


Key Details

Presents MathCoder method to enhance math reasoning of LLMs using code

Creates MathCodeInstruct dataset with math problems and code solutions

Proposes training approach to teach models to generate solutions with language, code, execution

MathCoder models achieve SOTA on math datasets among open-source LLMs

AI generated summary

Enabling LLMs to solve math problems with code

This paper presents a method to improve the mathematical reasoning abilities of large language models by integrating code generation and execution. The key ideas are creating a dataset of math problems paired with solutions that interleave natural language, code, and execution results, and a training approach that teaches models to produce such solutions.

Answers from this paper


No comments yet, be the first to start the conversation...

Sign up to comment on this paper

Sign Up