Skip to main content
Skip to main content

CLIP Talk: Valerie Chen (Carnegie Mellon)

Valerie Chen

CLIP Talk: Valerie Chen (Carnegie Mellon)

Maryland Language Science Center | Computational Linguistics and Information Processing Lab Wednesday, October 16, 2024 11:00 am - 12:00 pm Brendan Iribe Center, 4105

Towards a science of human-AI teams

Abstract: AI models have the potential to support and complement human decision-makers and users. And yet, the deployment of human-AI teams still faces practical challenges. I’m interested in developing a more principled workflow for building human-AI teams, which involves carefully examining points in the team setup and asking the following questions: (i) what are the right metrics to optimize the AI model for, and (ii) how can we facilitate effective communication between humans and AI. In this talk, I will discuss how existing literature has attempted to answer each of these questions, their limitations, and promising alternatives.

Bio: Valerie is a Machine Learning Ph.D. student at Carnegie Mellon University. Her research aims to improve human-AI interactions through a use-case-grounded lens and to leverage insights from practical user studies to design new interactive systems. Her research sits at the intersection of ML, NLP, and HCI. Valerie is a recipient of the NSF Graduate Research Fellowship, a former intern at MSR’s Fairness, Accountability, Transparency & Ethics in AI group, and a rising star in Data Science. Valerie completed her B.S. in Computer Science at Yale University.

Add to Calendar 10/16/24 11:00:00 10/16/24 12:00:00 America/New_York CLIP Talk: Valerie Chen (Carnegie Mellon)

Towards a science of human-AI teams

Abstract: AI models have the potential to support and complement human decision-makers and users. And yet, the deployment of human-AI teams still faces practical challenges. I’m interested in developing a more principled workflow for building human-AI teams, which involves carefully examining points in the team setup and asking the following questions: (i) what are the right metrics to optimize the AI model for, and (ii) how can we facilitate effective communication between humans and AI. In this talk, I will discuss how existing literature has attempted to answer each of these questions, their limitations, and promising alternatives.

Bio: Valerie is a Machine Learning Ph.D. student at Carnegie Mellon University. Her research aims to improve human-AI interactions through a use-case-grounded lens and to leverage insights from practical user studies to design new interactive systems. Her research sits at the intersection of ML, NLP, and HCI. Valerie is a recipient of the NSF Graduate Research Fellowship, a former intern at MSR’s Fairness, Accountability, Transparency & Ethics in AI group, and a rising star in Data Science. Valerie completed her B.S. in Computer Science at Yale University.

Brendan Iribe Center false

Organization

Website

CLIP Talks