CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective

OVERVIEW

CogMath evaluates the mathematical abilities of large language models through three stages inspired by human cognition: problem comprehension, problem solving, and solution summarization. It uses nine fine-grained dimensions to distinguish apparent answer accuracy from genuine mastery.

CITATION

@inproceedings{liu2025cogmath,
  title = {CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective},
  author = {Liu, Jiayu and Huang, Zhenya and Dai, Wei and Cheng, Cheng and Wu, Jinze and Sha, Jing and Li, Song and Liu, Qi and Wang, Shijin and Chen, Enhong},
  booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
  volume = {267},
  pages = {38692--38707},
  year = {2025},
  url = {https://proceedings.mlr.press/v267/liu25ab.html}
}