5 papers
The Perils of Agency: How Developers Perceive, Prioritize, and Address Risks in Agentic AI Products
Hao-Ping Lee, Jessica He, David Piorkowski +3
Agentic AI systems act autonomously, use tools, adapt to context, and operate in complex real-world environments. However, these same characteristics can create or exacerbate produ…
Promoting Critical Thinking With Domain-Specific Generative AI Provocations
Thomas Åerban von Davier, Hao-Ping Lee, Jodi Forlizzi +1
The evidence on the effects of generative AI (GenAI) on critical thinking is mixed, with studies suggesting both potential harms and benefits depending on its implementation. Some…
Sometimes You Need Facts, and Sometimes a Hug: Understanding Older Adults' Preferences for Explanations in LLM-Based Conversational AI Systems
Niharika Mathur, Tamara Zubatiy, Agata Rozga +2
Designing Conversational AI systems to support older adults requires these systems to explain their behavior in ways that align with older adults' preferences and context. While pr…
Situated, Dynamic, and Subjective: Envisioning the Design of Theory-of-Mind-Enabled Everyday AI with Industry Practitioners
Qiaosi Wang, Jini Kim, Avanita Sharma +4
Theory of Mind (ToM) -- the ability to infer what others are thinking (e.g., intentions) from observable cues -- is traditionally considered fundamental to human social interaction…
Rethinking Theory of Mind Benchmarks for LLMs: Towards A User-Centered Perspective
Qiaosi Wang, Xuhui Zhou, Maarten Sap +2
The last couple of years have witnessed emerging research that appropriates Theory-of-Mind (ToM) tasks designed for humans to benchmark LLM's ToM capabilities as an indication of L…