research
∙
03/28/2023
Foundation Models and Fair Use
Existing foundation models are trained on copyrighted material. Deployin...
share
research
∙
02/11/2023
Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks
Recent advances in instruction-following large language models (LLMs) ha...
research
∙
11/16/2022
Holistic Evaluation of Language Models
Language models (LMs) are becoming the foundation for almost all major l...
research
∙
10/25/2022
Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe
Privacy concerns have attracted increasing attention in data-driven prod...
research
∙
02/12/2021
Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations
We perform scalable approximate inference in a recently-proposed family ...
research
∙
06/18/2020
