The Boy Who Survived: Removing Harry Potter from an LLM is harder than reported

arXiv:2403.12082v1 Announce Type: cross
Abstract: Recent work arXiv.2310.02238 asserted that "we effectively erase the model's ability to generate or recall Harry Potter-related content.'' This claim is shown to be overbroad. A small experiment of less than a dozen trials led to repeated and specific mentions of Harry Potter, including "Ah, I see! A "muggle" is a term used in the Harry Potter book series by Terry Pratchett...''

abstract arxiv boy claim cs.ai cs.cl cs.lg experiment generate harry potter llm recall small type work