Knowledge Mechanisms in Large Language Models: A Survey and Perspective

Mengru Wang, Yunzhi Yao, Ziwen Xu, Shuofei Qiao, Shumin Deng, Peng Wang, Xiang Chen, Jia-Chen Gu, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang


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.
Anthology ID:
2024.findings-emnlp.416
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7097–7135
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.416
DOI:
10.18653/v1/2024.findings-emnlp.416
Bibkey:
Cite (ACL):
Mengru Wang, Yunzhi Yao, Ziwen Xu, Shuofei Qiao, Shumin Deng, Peng Wang, Xiang Chen, Jia-Chen Gu, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen, and Ningyu Zhang. 2024. Knowledge Mechanisms in Large Language Models: A Survey and Perspective. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 7097–7135, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Knowledge Mechanisms in Large Language Models: A Survey and Perspective (Wang et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.416.pdf