Computational Accounts of Trust in Human AI Interaction
By Zahra Zahedi
Abstract
The growing presence of AI-driven systems in our daily lives calls for the development
of efficient methods to facilitate interactions between humans and AI agents. At
the heart of these interactions lies the notion of trust, a key element shaping human
behavior and decision-making. It is essential to foster a suitable level of trust to
ensure the success of human-AI collaborations, while recognizing that excessive or
misplaced trust can lead to unfavorable consequences. Human-AI partnerships face
distinct hurdles, particularly potential misunderstandings about AI capabilities. This
emphasizes the need for AI agents to better understand and adjust human expectations
and trust.
The thesis explores the dynamics of trust in human-robot interactions, acknowledging
that the term encompasses human-AI interactions, and emphasizes the importance
of understanding trust in these relationships. This thesis first presents a mental
model-based framework that contextualizes trust in human-AI interactions, capturing
multi-faceted dimensions often overlooked in computational trust studies. Then, we
use this framework as a basis for developing decision-making frameworks that incorporate
trust in both single and longitudinal human-AI interactions. Finally, this mental
model-based framework enables us to infer and estimate trust when direct measures
are not feasible.
Thesis Committee
- Subbarao Kambhampati, Chair | Arizona State University
- Erin Chiou | Arizona State University
- Siddharth Srivastava | Arizona State University
- Yu Zhang | Arizona State University