2 papers
cs.CL2025
LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users
Almog Hilel, Riddhi Bhagwat, Idan Shenfeld +2
We describe a vulnerability in language models (LMs) trained with user feedback, whereby a single user can persistently alter LM knowledge and behavior given only the ability to pr…
cs.CL2025
Can Gradient Descent Simulate Prompting?
Eric Zhang, Leshem Choshen, Jacob Andreas
There are two primary ways of incorporating new information into a language model (LM): changing its prompt or changing its parameters, e.g. via fine-tuning. Parameter updates incu…