activity
20212025
most citedThe Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness

2 citations · 2 across the 3 of their papers we have counts for

collaborators
Showing 2025Show all

1 paper · 1 filter

cs.LG2025

Statistically Valid Post-Deployment Monitoring Should Be Standard for AI-Based Digital Health

Pavel Dolin, Weizhi Li, Gautam Dasarathy +1

This position paper argues that post-deployment monitoring in clinical AI is underdeveloped and proposes statistically valid and label-efficient testing frameworks as a principled…