4 papers
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…
Do LLMs Benefit From Their Own Words?
Jenny Y. Huang, Leshem Choshen, Wei Sun +6
In multi-turn conversations, large language models typically condition on the full conversation history: both past user prompts and assistant responses. We revisit this design choi…
Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models
Anna A. Ivanova, Aalok Sathe, Benjamin Lipkin +17
The ability to build and reason about models of the world is essential for situated language understanding. But evaluating world modeling capabilities in modern AI systems -- espec…
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…