arknet

AI & ML interests

None defined yet.

Recent Activity

wissamantoun  authored a paper 7 days ago

Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models

wissamantoun  authored a paper 7 days ago

Language-Switching Triggers Take a Latent Detour Through Language Models

wissamantoun  authored a paper 7 months ago

From Text to Source: Results in Detecting Large Language Model-Generated Content

View all activity

Team members 4