HenDav/value-steer-safety-head
Updated
Hen Davidov
HenDav
AI & ML interests
None yet
Recent Activity
upvoted a paper 10 days ago
From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs authored a paper 15 days ago
Selective Safety Steering via Value-Filtered Decoding authored a paper 15 days ago
Knowing When to Quit: A Principled Framework for Dynamic Abstention in LLM ReasoningOrganizations
