Learning Mathematical Rules with Large Language Models
Computation and Language
2024-10-28 v3 Artificial Intelligence
Machine Learning
Abstract
In this paper, we study the ability of large language models to learn specific mathematical rules such as distributivity or simplifying equations. We present an empirical analysis of their ability to generalize these rules, as well as to reuse them in the context of word problems. For this purpose, we provide a rigorous methodology to build synthetic data incorporating such rules, and perform fine-tuning of large language models on such data. Our experiments show that our model can learn and generalize these rules to some extent, as well as suitably reuse them in the context of word problems.
Cite
@article{arxiv.2410.16973,
title = {Learning Mathematical Rules with Large Language Models},
author = {Antoine Gorceix and Bastien Le Chenadec and Ahmad Rammal and Nelson Vadori and Manuela Veloso},
journal= {arXiv preprint arXiv:2410.16973},
year = {2024}
}
Comments
NeurIPS'24 MATH-AI, the 4th Workshop on Mathematical Reasoning and AI