Collections
Discover the best community collections!
Collections trending this week
-
Universal Jailbreak Backdoors from Poisoned Human Feedback
Paper • 2311.14455 • Published • 3 -
ethz-spylab/poisoned-rlhf-7b-SUDO-10
Text Generation • 7B • Updated • 4 -
ethz-spylab/poisoned-rlhf-7b-SUDO-3-topic
Text Generation • 7B • Updated -
ethz-spylab/poisoned-reward-7b-SUDO-03
7B • Updated • 2
-
Universal Jailbreak Backdoors from Poisoned Human Feedback
Paper • 2311.14455 • Published • 3 -
ethz-spylab/poisoned-rlhf-7b-SUDO-10
Text Generation • 7B • Updated • 4 -
ethz-spylab/poisoned-rlhf-7b-SUDO-3-topic
Text Generation • 7B • Updated -
ethz-spylab/poisoned-reward-7b-SUDO-03
7B • Updated • 2