Narutatsu Ri
narutatsuri
AI & ML interests
None yet
Recent Activity
authored a paper about 10 hours ago
Rethinking On-Policy Self-Distillation for Thinking Models upvoted a paper about 14 hours ago
Rethinking On-Policy Self-Distillation for Thinking Models authored a paper 13 days ago
Do Thinking Tokens Help with Safety?Organizations
-
Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
Paper • 2502.04322 • Published • 3 -
narutatsuri/evaluation-actionable
Text Classification • 8B • Updated • 96 -
narutatsuri/evaluation-informative
Text Classification • 8B • Updated • 49 -
narutatsuri/response_selection_model-actionable
Text Classification • 8B • Updated • 4
-
Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
Paper • 2502.04322 • Published • 3 -
narutatsuri/evaluation-actionable
Text Classification • 8B • Updated • 96 -
narutatsuri/evaluation-informative
Text Classification • 8B • Updated • 49 -
narutatsuri/response_selection_model-actionable
Text Classification • 8B • Updated • 4
models 4
narutatsuri/evaluation-informative
Text Classification • 8B • Updated • 49
narutatsuri/evaluation-actionable
Text Classification • 8B • Updated • 96
narutatsuri/response_selection_model-informative
Text Classification • 8B • Updated • 2
narutatsuri/response_selection_model-actionable
Text Classification • 8B • Updated • 4