6 papers
Conformal Policy Control
Drew Prinster, Clara Fannjiang, Ji Won Park +4
An agent must try new behaviors to explore and improve. In high-stakes environments, an agent that violates safety constraints may cause harm and must be taken offline, curtailing…
Toward Calibrated Mixture-of-Experts Under Distribution Shift
Gina Wong, Drew Prinster, Suchi Saria +2
Calibration aligns a model's predictive uncertainty with the frequencies of its empirical outcomes and is important for understanding and trusting reported probabilities. Recent wo…
Testing For Distribution Shifts with Conditional Conformal Test Martingales
Shalev Shaer, Yarin Bar, Drew Prinster +1
We propose a sequential test for detecting arbitrary distribution shifts that allows conformal test martingales (CTMs) to work under a fixed, reference-conditional setting. Existin…
E-valuator: Reliable Agent Verifiers with Sequential Hypothesis Testing
Shuvom Sadhuka, Drew Prinster, Clara Fannjiang +4
Agentic AI systems execute a sequence of actions, such as reasoning steps or tool calls, in response to a user prompt. To evaluate the success of their trajectories, researchers ha…
Improving Coverage in Combined Prediction Sets with Weighted p-values
Gina Wong, Drew Prinster, Suchi Saria +2
Conformal prediction quantifies the uncertainty of machine learning models by augmenting point predictions with valid prediction sets. For complex scenarios involving multiple tria…
WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales
Drew Prinster, Xing Han, Anqi Liu +1
Responsibly deploying artificial intelligence (AI) / machine learning (ML) systems in high-stakes settings arguably requires not only proof of system reliability, but also continua…