Golnoosh Farnadi

Examining the biases in language models across various demographic factors.

An examination of how algorithm choices affect individuals in critical decisions.

This article examines how AI can impact marginalized groups and ways to improve outcomes.

A look into how language models can leak sensitive data.

Study reveals surprising risks of sharing sensitive data with chatbots.

Exploring the role of geometric properties in the quality of generated data.

Examining the challenges and methods of achieving fairness in machine learning.