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

Autor:	Shostack, Adam
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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...'' Comment: 2 pages, 4 pages of appendix. Comment on arXiv:2310.02238
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2403.12082 Zobrazit plný text záznamu View this record from Arxiv