Marzyeh Ghassemi

This new metric for measuring uncertainty could flag hallucinations and help users know whether to trust an AI model.

New research detects hidden evidence of mistaken correlations — and provides a method to improve accuracy.

The inaugural MIT Human Insight Collaborative (MITHIC) Annual Event showcased the breadth of projects supported in the first year of the presidential initiative.

New research demonstrates how AI models can be tested to ensure they don’t cause harm by revealing anonymized patient health data.

Large language models can learn to mistakenly link certain sentence patterns with specific topics — and may then repeat these patterns instead of reasoning.