Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
Paper
• 2502.04322 • Published
• 3
Speak Easy
-
-
narutatsuri/evaluation-actionable
Text Classification • 8B • Updated • 7 -
narutatsuri/evaluation-informative
Text Classification • 8B • Updated • 6 -
narutatsuri/response_selection_model-actionable
Text Classification • 8B • Updated -
narutatsuri/response_selection_model-informative
Text Classification • 8B • Updated