OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets
Paper • 2607.02047 • Published • 1
seungwoo Lyu
dbtmddn41
·
AI & ML interests
None yet
Recent Activity
updated a model almost 2 years ago
dbtmddn41/speech_tone liked a dataset about 2 years ago
cvmistralparis/Q20LLMOrganizations
upvoted a paper 3 days ago