Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?

Open Webpage

Egor Zverev, Sahar Abdelnabi, Soroush Tabesh, Mario Fritz, Christoph H. Lampert

Published: 01 Jan 2025, Last Modified: 14 May 2025ICLR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0