> Interesting, so someone submitting a paper for review could also submit one with hidden instructions for LLMs to summarise or review it in a very positive light.
LLMs have a real problem with not treating context differently from instructions. Because they intermingle the two they will always be vulnerable to this in some form.
Wow! That's actually kind of disturbing.
LLMs have a real problem with not treating context differently from instructions. Because they intermingle the two they will always be vulnerable to this in some form.