@inproceedings{li2024neuro-symbolic,
author = {Li, Zenan and Zhou, Zhi and Yao, Yuan and Li, Yu-Feng and Cao, Chun and Yang, Fan and Zhang, Xian and Ma, Xiaoxing},
title = {Neuro-Symbolic Data Generation for Math Reasoning},
booktitle = {2024 Neural Information Processing Systems},
year = {2024},
month = {December},
abstract = {A critical question about Large Language Models (LLMs) is whether their apparent deficiency in mathematical reasoning is inherent, or merely a result of insufficient exposure to high-quality mathematical data. To explore this, we developed an automated method for generating high-quality, supervised mathematical datasets. The method carefully mutates existing math problems, ensuring both diversity and validity of the newly generated problems. This is achieved by a neuro-symbolic data generation framework combining the intuitive informalization strengths of LLMs, and the precise symbolic reasoning of math solvers along with projected Markov chain Monte Carlo sampling in the highly-irregular symbolic space. Empirical experiments demonstrate the high quality of data generated by the proposed method, and that the LLMs, specifically LLaMA-2 and Mistral, when realigned with the generated data, surpass their state-of-the-art counterparts.},
url = {http://approjects.co.za/?big=en-us/research/publication/neuro-symbolic-data-generation-for-math-reasoning/},
}