Knowledge Mechanisms in Large Language Models: A Survey and Perspective

Mengru Wang, Yunzhi Yao, Shuofei Qiao, Shumin Deng, Jia-Chen Gu, Fei Huang, Huajun Chen, Ningyu Zhang

Keywords: knowledge mechanism, life cycle, survey

Abstract: 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.

Archival Status: Non-archival (not included in proceedings)

Submission Number: 58