activity
20172025
most citedAssessing Post-Disaster Damage from Satellite Imagery using Semi-Supervised Learning Techniques

27 citations · 102 across the 20 of their papers we have counts for

collaborators
Showing 2023 · cs.CLShow all

1 paper · 2 filters

cs.CL2023

Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?

C. Daniel Freeman, Laura Culp, Aaron Parisi +27

We introduce and study the problem of adversarial arithmetic, which provides a simple yet challenging testbed for language model alignment. This problem is comprised of arithmetic…