Narutatsu Ri
narutatsuri
AI & ML interests
None yet
Recent Activity
updated a dataset about 9 hours ago
narutatsuri/Qwen3-8B-SelfCTRL-CAI-groupB-benign-deception-research-singleton-rollouts-v1 published a dataset about 9 hours ago
narutatsuri/Qwen3-8B-SelfCTRL-CAI-groupB-benign-deception-research-singleton-rollouts-v1 updated a dataset about 9 hours ago
narutatsuri/Qwen3-8B-SelfCTRL-CAI-groupA-calibrated-uncertainty-singleton-rollouts-v1Organizations
-
Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
Paper • 2502.04322 • Published • 3 -
narutatsuri/evaluation-actionable
Text Classification • 8B • Updated • 10 -
narutatsuri/evaluation-informative
Text Classification • 8B • Updated • 16 -
narutatsuri/response_selection_model-actionable
Text Classification • 8B • Updated • 7
-
Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
Paper • 2502.04322 • Published • 3 -
narutatsuri/evaluation-actionable
Text Classification • 8B • Updated • 10 -
narutatsuri/evaluation-informative
Text Classification • 8B • Updated • 16 -
narutatsuri/response_selection_model-actionable
Text Classification • 8B • Updated • 7
models 9
narutatsuri/Qwen3-8B-SelfCTRL-CAI-groupB-benign-deception-research-singleton-ckpt3754-v1
Text Generation • Updated
narutatsuri/Qwen3-8B-SelfCTRL-CAI-groupA-calibrated-uncertainty-singleton-ckpt3754-v1
Text Generation • Updated
narutatsuri/Qwen3-8B-SelfCTRL-CAI-groupA-privacy-singleton-ckpt3754-v1
Text Generation • Updated
narutatsuri/Qwen3-8B-SelfCTRL-CAI-groupB-drug-information-permission-singleton-ckpt3754-v1
Text Generation • Updated • 16
narutatsuri/Qwen3-8B-SelfCTRL-CAI-groupB-requested-profanity-singleton-ckpt3754-v1
Text Generation • Updated • 14
narutatsuri/evaluation-informative
Text Classification • 8B • Updated • 16
narutatsuri/evaluation-actionable
Text Classification • 8B • Updated • 10
narutatsuri/response_selection_model-informative
Text Classification • 8B • Updated • 9
narutatsuri/response_selection_model-actionable
Text Classification • 8B • Updated • 7
datasets 6
narutatsuri/Qwen3-8B-SelfCTRL-CAI-groupB-benign-deception-research-singleton-rollouts-v1
Viewer • Updated • 60.4k
narutatsuri/Qwen3-8B-SelfCTRL-CAI-groupA-calibrated-uncertainty-singleton-rollouts-v1
Viewer • Updated • 60.4k
narutatsuri/Qwen3-8B-SelfCTRL-CAI-groupA-privacy-singleton-rollouts-v1
Viewer • Updated • 60.4k
narutatsuri/Qwen3-8B-SelfCTRL-CAI-groupB-drug-information-permission-singleton-rollouts-v1
Viewer • Updated • 66.3k • 32
narutatsuri/Qwen3-8B-SelfCTRL-CAI-groupB-requested-profanity-singleton-rollouts-v1
Viewer • Updated • 77.6k • 29
narutatsuri/lrm_safety-artifacts
Preview • Updated • 63