A Mentalistic Interface for Probing Folk-Psychological Attribution to Non-Humanoid Robots

TL;DR

This paper introduces an experimental platform that uses language and framing to study how humans attribute mental states to non-humanoid robots, aiding understanding of folk-psychological attribution.

Contribution

It presents a novel system combining simulated robots, realistic environments, and language models to control and analyze attribution processes in robotics.

Findings

Language framing influences attribution of mental states

Controlled experiments isolate effects of explanatory frames

Platform enables systematic study of folk-psychology in robotics

Abstract

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.