LLM Safety From Within: Detecting Harmful Content with Internal Representations
Paper • 2604.18519 • Published • 26
Linfeng Du
linfeng-du
AI & ML interests
None yet
Recent Activity
upvoted a paper 12 days ago
LLM Safety From Within: Detecting Harmful Content with Internal Representations upvoted a paper 27 days ago
ClawBench: Can AI Agents Complete Everyday Online Tasks?Organizations
None yet
upvoted a paper 12 days ago