Tell Me Something That Will Help Me Trust You: A Survey of Trust Calibration in Human-Agent Interaction
This addresses the challenge of trust calibration for users interacting with AI agents, but it is incremental as it synthesizes existing research into a taxonomy.
The paper tackles the problem of what additional information humans need from intelligent agents to decide whether to trust their predictions or recommendations, resulting in a taxonomy based on a survey of literature in human-agent interaction.
When a human receives a prediction or recommended course of action from an intelligent agent, what additional information, beyond the prediction or recommendation itself, does the human require from the agent to decide whether to trust or reject the prediction or recommendation? In this paper we survey literature in the area of trust between a single human supervisor and a single agent subordinate to determine the nature and extent of this additional information and to characterize it into a taxonomy that can be leveraged by future researchers and intelligent agent practitioners. By examining this question from a human-centered, information-focused point of view, we can begin to compare and contrast different implementations and also provide insight and directions for future work.