LLM Safety From Within: Detecting Harmful Content with Internal Representations
Paper • 2604.18519 • Published • 24
Haoyu Xu
hyyy88
AI & ML interests
None yet
Recent Activity
upvoted a paper 10 days ago
LLM Safety From Within: Detecting Harmful Content with Internal RepresentationsOrganizations
None yet
upvoted a paper 10 days ago