LLM Safety From Within: Detecting Harmful Content with Internal Representations
Paper • 2604.18519 • Published • 24
Linfeng Du
linfeng-du
AI & ML interests
None yet
Recent Activity
upvoted a paper 10 days ago
LLM Safety From Within: Detecting Harmful Content with Internal Representations upvoted a paper 25 days ago
ClawBench: Can AI Agents Complete Everyday Online Tasks?Organizations
None yet
upvoted a paper 10 days ago