Recently, there has been a growing interest in knowledge editing for Large Language
Models (LLMs). Current approaches and evaluations merely explore the instance-level …

This paper investigates using knowledge editing techniques to detoxify Large Language
Models (LLMs). We construct a benchmark, SafeEdit, which covers nine unsafe categories …

As large language models (LLMs) are widely deployed, targeted editing of their knowledge
has become a critical challenge. Recently, advancements in model editing techniques, such …

Humans rarely learn one fact in isolation. Instead, learning a new fact induces knowledge of
other facts about the world. For example, in learning a korat is a type of cat, you also infer it …

Large language models (LLMs) have revolutionized knowledge storage and retrieval, but
face challenges with conflicting and outdated information. Knowledge editing techniques …