Understanding knowledge mechanisms in Large Language Models (LLMs) is crucial for advancing towards trustworthy AGI. This paper reviews knowledge mechanism analysis from a novel taxonomy including knowledge utilization and evolution. Knowledge utilization delves into the mechanism of memorization, comprehension and application, and creation. Knowledge evolution focuses on the dynamic progression of knowledge within individual and group LLMs. Moreover, we discuss what knowledge LLMs have learned, the reasons for the fragility of parametric knowledge, and the potential dark knowledge (hypothesis) that will be challenging to address. We hope this work can help understand knowledge in LLMs and provide insights for future research.
@article{arxiv.2407.15017,
title = {Knowledge Mechanisms in Large Language Models: A Survey and Perspective},
author = {Mengru Wang and Yunzhi Yao and Ziwen Xu and Shuofei Qiao and Shumin Deng and Peng Wang and Xiang Chen and Jia-Chen Gu and Yong Jiang and Pengjun Xie and Fei Huang and Huajun Chen and Ningyu Zhang},
journal= {arXiv preprint arXiv:2407.15017},
year = {2024}
}