no code implementations • 27 May 2024 • Jun-Yu Ma, Hong Wang, Hao-Xiang Xu, Zhen-Hua Ling, Jia-Chen Gu
In this paper, we first theoretically analyze that the factor affecting the general abilities in sequential model editing lies in the condition number of the edited matrix.
1 code implementation • 9 Jan 2024 • Jia-Chen Gu, Hao-Xiang Xu, Jun-Yu Ma, Pan Lu, Zhen-Hua Ling, Kai-Wei Chang, Nanyun Peng
One critical challenge that has emerged is the presence of hallucinations in the output of large language models (LLMs) due to false or outdated knowledge.