Bias in Generative AI

no code implementations • 5 Mar 2024 • Mi Zhou, Vibhanshu Abhishek, Timothy Derdenger, Jaymo Kim, Kannan Srinivasan

Moreover, we found that the evident gender and racial biases uncovered in our analysis were even more pronounced than the status quo when compared to labor force statistics or Google images, intensifying the harmful biases we are actively striving to rectify in our society.

Regulating eXplainable Artificial Intelligence (XAI) May Harm Consumers

no code implementations • 7 Sep 2022 • Behnam Mohammadi, Nikhil Malik, Tim Derdenger, Kannan Srinivasan

eXplainable AI (XAI) is a class of methods that seek to address lack of AI interpretability and trust by explaining to customers their AI decisions.

Explainable artificial intelligence Explainable Artificial Intelligence (XAI) +1