A Grounded Observer Framework for Establishing Guardrails for Foundation Models in Socially Sensitive Domains
Ramnauth, Rebecca, Brščić, Dražen, Scassellati, Brian
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Dec-23-2024
- Country:
- North America > United States
- Indiana > Lake County
- Griffith (0.04)
- Connecticut > New Haven County
- New Haven (0.04)
- Indiana > Lake County
- Europe > United Kingdom
- Asia > Japan
- Honshū > Kansai > Kyoto Prefecture > Kyoto (0.04)
- North America > United States
- Genre:
- Research Report > Experimental Study (0.69)
- Industry:
- Education (1.00)
- Health & Medicine > Therapeutic Area
- Psychiatry/Psychology (0.34)
- Technology:
- Information Technology > Artificial Intelligence
- Robots (1.00)
- Representation & Reasoning (1.00)
- Natural Language
- Large Language Model (1.00)
- Chatbot (0.69)
- Machine Learning > Neural Networks
- Deep Learning (0.69)
- Information Technology > Artificial Intelligence