Hi! I’m a PhD candidate at the University of Washington advised by Dan Weld. My research is in the area of human-AI interaction. More specifically, I enjoy investigating methods to support end users’ verification and control of AI suggestions. Most often, I study these methods for applications to scientific communication and in the context of LLM-powered tools or recommender systems.

Email: radensky@cs.washington.edu

CV | LinkedIn | Semantic Scholar | Google Scholar

Currently

• Research assistant at the University of Washington

Previous Research Internships

• Allen Institute for AI (Summer 2023, Summer 2020)

• Google (Summer 2022)

• Microsoft (Summer 2021)

Publications

• “I Think You Might Like This”: Exploring Effects of Confidence Signal Patterns on Trust in and Reliance on Conversational Recommender Systems
Marissa Radensky, Julie Anne Séguin, Jang Soo Lim, Kristen Olson, Robert Geiger (FAccT 2023)

• Bursting Scientific Filter Bubbles: Boosting Innovation via Novel Author Discovery
Jason Portenoy, Marissa Radensky, Jevin West, Eric Horvitz, Daniel S. Weld, and Tom Hope (CHI 2022)

• PUMICE: A Multi-Modal Agent that Learns Concepts and Conditionals from Natural Language and Demonstrations
Toby Jia-Jun Li, Marissa Radensky, Justin Jia, Kirielle Singarajah, Tom M. Mitchell, and Brad A. Myers (UIST 2019)

• The Story in the Notebook: Exploratory Data Science using a Literate Programming Tool
Mary Beth Kery, Marissa Radensky, Mahima Arya, Bonnie E. John, and Brad A. Myers (CHI 2018)

Workshop Papers and Extended Abstracts

• Exploring How Anomalous Model Input and Output Alerts Affect Decision-Making in Healthcare
Marissa Radensky, Dustin Burson, Rajya Bhaiya, and Daniel S. Weld (CHI 2022 Workshop on Trust and Reliance in AI-Human Teams)

• Exploring the Role of Local and Global Explanations in Recommender Systems
Marissa Radensky, Doug Downey, Kyle Lo, Zoran Popović, and Daniel S. Weld (CHI 2022 Late-Breaking Work)

• Interactive Task and Concept Learning from Natural Language Instructions and GUI Demonstrations
Toby Jia-Jun Li, Marissa Radensky, Justin Jia, Kirielle Singarajah, Tom M. Mitchell, and Brad A. Myers (IPA 2020 Workshop)

• A Multi-Modal Approach to Concept Learning in Task Oriented Conversational Agents
Toby Jia-Jun Li, Marissa Radensky, Tom M. Mitchell, and Brad A. Myers (CHI 2019 Workshop)

• How End Users Express Conditionals in Programming by Demonstration for Mobile Apps
Marissa Radensky, Toby Jia-Jun Li, and Brad A. Myers (VL/HCC 2018 Poster)