A Grounded Observer Framework for Establishing Guardrails for Foundation Models in Socially Sensitive Domains

TL;DR

This paper introduces a grounded observer framework that constrains foundation model behavior in sensitive domains by providing real-time feedback and behavioral guarantees, demonstrated through conversational interactions with a robot.

Contribution

It presents a novel framework inspired by robotic action selection to dynamically constrain foundation models in high-dimensional, socially sensitive settings.

Findings

Successfully maintained contextually appropriate conversations.

Enabled real-time behavioral adjustments based on low-level assessments.

Applied framework to human-robot interactions for unscripted social engagement.

Abstract

As foundation models increasingly permeate sensitive domains such as healthcare, finance, and mental health, ensuring their behavior meets desired outcomes and social expectations becomes critical. Given the complexities of these high-dimensional models, traditional techniques for constraining agent behavior, which typically rely on low-dimensional, discrete state and action spaces, cannot be directly applied. Drawing inspiration from robotic action selection techniques, we propose the grounded observer framework for constraining foundation model behavior that offers both behavioral guarantees and real-time variability. This method leverages real-time assessment of low-level behavioral characteristics to dynamically adjust model actions and provide contextual feedback. To demonstrate this, we develop a system capable of sustaining contextually appropriate, casual conversations ("small talk"), which we then apply to a robot for novel, unscripted interactions with humans. Finally, we discuss potential applications of the framework for other social contexts and areas for further research.