PhD Proposal by Kantwon Rogers
What Happens When a Robot Lies to You?
Investigating Aspects of Prosocial Intelligent Agent Deception Towards Humans
Date: December 6th, 2023
Time: 3:00PM-5:00PM EST
Location: Virtual Zoom Meeting
Meeting ID: 954 9001 6600
Ph.D. student in Computer Science
School of Interactive Computing
Georgia Institute of Technology
Dr. Sonia Chernova – (co-advisor) College of Computing, Georgia Institute of Technology
Dr. Ayanna Howard – (co-advisor) College of Computing, Georgia Institute of Technology / College of Engineering, Ohio State University
Dr. Ashok Goel – College of Computing, Georgia Institute of Technology
Dr. Harish Ravichandar – College of Computing, Georgia Institute of Technology
Dr. Selma Šabanović – School of Informatics and Computing, Indiana University Bloomington
Dr. Marynel Vázquez – Department of Computer Science, Yale University
People across many societies are explicitly taught some form of the adage “honesty is the best policy”, but is that a lie? Telling the truth is not always helpful, and lying is not always harmful. In truth, everyone lies. We lie to help ourselves, and we lie to help others. We lie in both serious and inconsequential situations. Lying is a foundational part of how people interact with each other, and accepted members of society are successfully able to navigate the highly nuanced norms of social deception.
Robots and artificially intelligent systems are increasingly being placed within our societies, and in some contexts, they are expected to interact with humans socially. People must trust that robots are functionally competent to complete tasks while also being socially competent to understand social conventions that may favor particular strategies over others. If people often successfully choose lying to be the best policy in certain situations, it then follows that an intelligent agent, that is designed to learn from humans and exhibit social competency, may replicate expected lying behavior as it becomes fully integrated into social settings.
In this thesis, I explore intelligent agents that lie to benefit others and how deception influences people’s interactions and perceptions of them. Additionally, my work studies the effect of the timing at which users realize an intelligent agent can, or has, lied to them: before an interaction, during an interaction, or after an interaction.
The proposed work details my plan for creating and evaluating an autonomous deceptive agent using large language models within a longitudinal educational context.
- Workflow Status:Published
- Created By:Tatianna Richardson
- Modified By:Tatianna Richardson