The Boy Who Survived: Removing Harry Potter from an LLM is harder than reported
arXiv:2403.12082
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...''
2 pages, 4 pages of appendix. Comment on arXiv:2310.02238