See the Unseen: Better Context-Consistent Knowledge-Editing by Noises
This addresses the issue of limited generalization in knowledge editing for LLMs, which is incremental as it builds on existing editing methods.
The paper tackles the problem of context-consistent knowledge editing in large language models (LLMs) by using Gaussian noise to simulate unseen contexts, improving editing generalization with experimental results on three LLMs.
Knowledge-editing updates knowledge of large language models (LLMs) and contributes to the interpretability and application of LLMs. However, knowledge applying is context-consistent: LLMs can recall the same knowledge in different contexts. Existing works ignore this property and the editing lacks generalization. In this paper, we empirically find that the effects of different contexts upon LLMs in recalling the same knowledge follow a Gaussian-like distribution. We then sample Gaussian noises to simulate the effects of different contexts when updating LLMs. By such, we can make LLMs see the unseen contexts where the edited knowledge will be applied, therefore improving the editing generalization. Experimental results on three LLMs demonstrate the effectiveness of our methods and also distinguish our methods from the others of fine-tuning LLMs by noises.