AI-SDM Seminar - Valerie Chen February 14, 2025 3:00pm — 4:30pm Location: In Person and Virtual - ET - Newell Simon 4305 and Zoom Speaker: VALERIE CHEN, Ph.D. Student, Machine Learning Department, Carnegie Mellon University https://valeriechen.github.io/ The evolving AI landscape means that models have the potential to support human decision-makers and users in a wide range of fields and applications. And yet, human-AI interactions in many deployment contexts still face practical challenges. In this talk, we discuss how to design and evaluate these interactions in two common paradigms. The first half focuses on predictive decision-making, and the role of explanations in facilitating appropriate reliance on AI recommendations. The second half explores more complex settings where AI are “copilots”, highlighting gaps in existing evaluations and proposing a new in-the-wild framework. We conclude by discussing common themes across paradigms and lessons learned for building effective human-AI interactions.—Valerie Chen is a Machine Learning Ph.D. student at CMU. Her research aims to improve human-AI interactions by leveraging 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 was selected as a Rising Star in Data Science.REGISTER → upon registration, confirmation information on joining the meeting will be provided Event Website: https://www.cmu.edu/ai-sdm/events/index.html Add event to Google Add event to iCal
