FineMath: A Fine-Grained Mathematical Evaluation Benchmark for Chinese Large Language Models
This work addresses the need for better evaluation of mathematical reasoning in Chinese LLMs, though it is incremental as it focuses on dataset creation and benchmarking.
The authors introduced FineMath, a fine-grained benchmark dataset for evaluating Chinese large language models on elementary school math word problems across 17 categories and difficulty levels, finding that current models have significant room for improvement in mathematical reasoning.
To thoroughly assess the mathematical reasoning abilities of Large Language Models (LLMs), we need to carefully curate evaluation datasets covering diverse mathematical concepts and mathematical problems at different difficulty levels. In pursuit of this objective, we propose FineMath in this paper, a fine-grained mathematical evaluation benchmark dataset for assessing Chinese LLMs. FineMath is created to cover the major key mathematical concepts taught in elementary school math, which are further divided into 17 categories of math word problems, enabling in-depth analysis of mathematical reasoning abilities of LLMs. All the 17 categories of math word problems are manually annotated with their difficulty levels according to the number of reasoning steps required to solve these problems. We conduct extensive experiments on a wide range of LLMs on FineMath and find that there is still considerable room for improvements in terms of mathematical reasoning capability of Chinese LLMs. We also carry out an in-depth analysis on the evaluation process and methods that have been overlooked previously. These two factors significantly influence the model results and our understanding of their mathematical reasoning capabilities. The dataset will be publicly available soon.