Neel Jain
nsjain
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 2 months ago
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLM
authored
a paper
2 months ago
Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language
Models
authored
a paper
2 months ago
DynaGuard: A Dynamic Guardrail Model With User-Defined Policies
Organizations
