A Mentalistic Interface for Probing Folk-Psychological Attribution to Non-Humanoid Robots
This addresses the challenge of understanding human-robot interaction for researchers in psychology and robotics, though it is incremental as it builds on existing frameworks for intentional attribution.
The paper tackles the problem of studying how people attribute intentional states to non-humanoid robots by developing an experimental platform that combines a simulated robot, task environments, and large language model-based explanatory layers to express behavior in mentalistic, teleological, or mechanistic terms, with the result being a controlled method to investigate the influence of language and framing on intentional stance adoption.
This paper presents an experimental platform for studying intentional-state attribution toward a non-humanoid robot. The system combines a simulated robot, realistic task environments, and large language model-based explanatory layers that can express the same behavior in mentalistic, teleological, or mechanistic terms. By holding behavior constant while varying the explanatory frame, the platform provides a controlled way to investigate how language and framing shape the adoption of the intentional stance in robotics.