We-Math

# Dataset Card for WE-MATH (ACL 2025)

[GitHub](https://github.com/We-Math/We-Math) | [Paper](https://arxiv.org/pdf/2407.01284) | [Website](https://we-math.github.io/)

Inspired by human-like mathematical reasoning, we introduce We-Math, the first benchmark specifically designed to explore the problem-solving principles beyond the end-to-end performance. We meticulously collect and categorize 6.5K visual math problems, spanning 67 hierarchical knowledge concepts and 5 layers of knowledge granularity.

## Citation
If you find the content of this project helpful, please cite our paper as follows:

```
@article{qiao2024we,
title={We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?},
author={Qiao, Runqi and Tan, Qiuna and Dong, Guanting and Wu, Minhui and Sun, Chong and Song, Xiaoshuai and GongQue, Zhuoma and Lei, Shanglin and Wei, Zhe and Zhang, Miaoxuan and others},
journal={arXiv preprint arXiv:2407.01284},
year={2024}
}
```

# 数据集卡片：WE-MATH（ACL 2025）
[GitHub](https://github.com/We-Math/We-MATH) | [论文](https://arxiv.org/pdf/2407.01284) | [官网](https://we-math.github.io/)

受类人数学推理的启发，我们推出了WE-MATH——首个专为探索超越端到端性能的解题原理而设计的基准数据集。我们精心收集并分类了6.5K道视觉数学题，涵盖67个层级化知识概念与5个层级的知识粒度。

## 引用
若您认为本项目内容对您有所帮助，请按以下格式引用我们的论文：

@article{qiao2024we,
title={WE-MATH：你的多模态大模型（Large Multimodal Model）能否实现类人数学推理？},
author={Qiao, Runqi and Tan, Qiuna and Dong, Guanting and Wu, Minhui and Sun, Chong and Song, Xiaoshuai and GongQue, Zhuoma and Lei, Shanglin and Wei, Zhe and Zhang, Miaoxuan and others},
journal={arXiv预印本 arXiv:2407.01284},
year={2024}
}

搜集汇总

背景与挑战

背景概述

We-Math是一个专门设计用于探索超越端到端性能的问题解决原则的基准，它精心收集并分类了6.5K个视觉数学问题，涵盖67个层次化知识概念和5个知识粒度层级。该数据集旨在评估大型多模态模型是否实现类人数学推理能力。