LLM Safety From Within: Detecting Harmful Content with Internal Representations
Paper • 2604.18519 • Published • 19
Joseph Tang
lilvjosephtang
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
LLM Safety From Within: Detecting Harmful Content with Internal Representations authored a paper 20 days ago
ChessQA: Evaluating Large Language Models for Chess Understanding authored a paper 20 days ago
ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-RefinementOrganizations
upvoted a paper 1 day ago
upvoted a paper 24 days ago
upvoted an article 6 months ago
Article
Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment
•
119