MARIO Eval: Evaluate Your Math LLM with your Math LLM--A mathematical dataset evaluation toolkit

TL;DR

This paper introduces a comprehensive evaluation toolkit for mathematical language models that combines a computer algebra system with an optional LLM, enabling more consistent and robust assessments across different datasets.

Contribution

The authors present a unified, generalizable evaluation toolkit for math LLMs that integrates CAS and optional LLM, improving evaluation consistency and robustness.

Findings

The toolkit provides more robust evaluation results than prior methods.

Incorporating an LLM enhances evaluation accuracy.

The toolkit is validated on two distinct datasets.

Abstract

Large language models (LLMs) have been explored in a variety of reasoning tasks including solving of mathematical problems. Each math dataset typically includes its own specially designed evaluation script, which, while suitable for its intended use, lacks generalizability across different datasets. Consequently, updates and adaptations to these evaluation tools tend to occur without being systematically reported, leading to inconsistencies and obstacles to fair comparison across studies. To bridge this gap, we introduce a comprehensive mathematical evaluation toolkit that not only utilizes a python computer algebra system (CAS) for its numerical accuracy, but also integrates an optional LLM, known for its considerable natural language processing capabilities. To validate the effectiveness of our toolkit, we manually annotated two distinct datasets. Our experiments demonstrate that the toolkit yields more robust evaluation results compared to prior works, even without an LLM. Furthermore, when an LLM is incorporated, there is a notable enhancement. The code for our method will be made available at \url{https://github.com/MARIO-Math-Reasoning/math_evaluation}.