Please join us for an interaction session to test GenAI models for potential issues with biases, inaccuracies, and other matters related to healthcare. Red-teaming is a form of evaluation that elicits model vulnerabilities that might lead to undesirable behaviors. We will be looking for such behaviors on healthcare-related tasks.
All faculty, graduate students and postdocs are welcome. We will break into groups with table leaders from Stanford Healthcare, School of Medicine, CS and external partners providing technical and clinical insights. At the end we’ll have a read-out of findings, and then continue the conversations during happy hour.
Date: October 25th
Location: Chem-H Building Room E241
Agenda:
3:00pm | Check in begins
3:15pm | Table groups begin Red Teaming
4:45pm | Happy hour
6:00pm | Event concludes
If you have questions, please contact Roxana Daneshjou or Karen Matthys. Faculty, if you’re interested in leading a table group please let us know.
