Learning Mathematical Rules with Large Language Models

Antoine Gorceix, Bastien Le Chenadec, Ahmad Rammal, Nelson Vadori, Manuela Veloso

Keywords: llm, large language models, mathematical reasoning

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.

Concurrent Submissions: N/A

Submission Number: 16