MARIO Eval: Evaluate Your Math LLM with your Math LLM--A mathematical dataset evaluation toolkit
This toolkit addresses the issue of fair comparison across studies in mathematical reasoning for researchers, but it is incremental as it builds on existing evaluation methods.
The authors tackled the problem of inconsistent and non-generalizable evaluation scripts for mathematical datasets by introducing a comprehensive toolkit that uses a computer algebra system and optionally integrates an LLM, resulting in more robust evaluation results and notable enhancements when an LLM is included.
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}.