Can Editing LLMs Inject Harm?
Knowledge editing techniques have been increasingly adopted to efficiently correct the false
or outdated knowledge in Large Language Models (LLMs), due to the high cost of retraining …
or outdated knowledge in Large Language Models (LLMs), due to the high cost of retraining …
Detoxifying Large Language Models via Knowledge Editing
This paper investigates using knowledge editing techniques to detoxify Large Language
Models (LLMs). We construct a benchmark, SafeEdit, which covers nine unsafe categories …
Models (LLMs). We construct a benchmark, SafeEdit, which covers nine unsafe categories …