Can I read The Curse of Popularity: Popular Entities have Catastrophic Side Effects when Deleting Knowledge from Language Models on EtoBox?

The Curse of Popularity: Popular Entities have Catastrophic Side Effects when Deleting Knowledge from Language Models by Takahashi, Ryosuke; Kamoda, Go; Heinzerling, Benjamin; Sakaguchi, Keisuke; Inui, Kentaro is a scholarly article available to read on EtoBox.

What is The Curse of Popularity: Popular Entities have Catastrophic Side Effects when Deleting Knowledge from Language Models about?

Language models (LMs) encode world knowledge in their internal parameters through training. However, LMs may learn personal and confidential information from the training data, leading to privacy concerns such as data leakage. Therefore, research on knowledge deletion from LMs is essential. This study focuses on the knowledge stored in LMs and analyzes the relationship between the side effects of knowledge deletion and the entities related to the knowledge. Our findings reveal that deleting knowledge related to popular entities can have catastrophic side effects. Furthermore, this research is the first to analyze knowledge deletion in models trained on synthetic knowledge graphs, indicating a new direction for controlled experiments.

Author

Takahashi, Ryosuke; Kamoda, Go; Heinzerling, Benjamin; Sakaguchi, Keisuke; Inui, Kentaro

Published

2024

Language

EN