What Do You Think I Think? Accounting for Human Beliefs Using Second-Order Theory of Mind
Discrepancies between an agent's actual knowledge and what a person thinks the agent knows can hinder interactions. If an agent could detect such discrepancies, it could provide feedback to account for them and improve current and future interactions. Using the I-POMDP as a framework for a second-order Theory of Mind (ToM-2), this work endows an agent with the ability to model the evolution of a person's erroneous beliefs about an agent and the cognitive biases and heuristics (CBH) from which they arise. In doing so, the agent can detect when CBH might be at play during an interaction and adaptively generate feedback that accounts for them. An in-person user study shows how a ToM-2 learner can account for the effects of a teacher's CBH to significantly improve the informativeness of teacher actions, and subjective results suggest people find the ToM-2 learner's feedback more useful.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
On the Utility of Accounting for Human Beliefs about AI Intention in Human-AI Collaboration
To enable effective human-AI collaboration, merely optimizing AI performance without considering human factors is insufficient. Recent research has shown that designing AI agents that take human behavior into account lea…
AI AgentWishful Thinking is Risky Thinking
We develop a model of wishful thinking that incorporates the costs and benefits of biased beliefs. We establish the connection between distorted beliefs and risk, revealing how wishful thinking can be understood in terms…
Learning what they think vs. learning what they do: The micro-foundations of vicarious learning
Vicarious learning is a vital component of organizational learning. We theorize and model two fundamental processes underlying vicarious learning: observation of actions (learning what they do) vs. belief sharing (learni…
Grounding Language about Belief in a Bayesian Theory-of-Mind
Despite the fact that beliefs are mental states that cannot be directly observed, humans talk about each others' beliefs on a regular basis, often using rich compositional language to describe what others think and know.…
AttributeInterventions Against Machine-Assisted Statistical Discrimination
I study statistical discrimination driven by verifiable beliefs, such as those generated by machine learning, rather than by humans. When beliefs are verifiable, interventions against statistical discrimination can move …
Fairness