Thoughtful Things: Building Human-Centric Smart Devices with Small Language Models
This addresses usability issues in smart devices for everyday users by enabling more intuitive, private interactions, though it is incremental as it builds on existing language model and formal modeling techniques.
The authors tackled the problem of smart devices being complicated to use by proposing 'thoughtful things' that use on-device small language models to respond to unconstrained commands and explain behaviors, achieving deployment on real hardware without cloud dependency.
Everyday devices like light bulbs and kitchen appliances are now embedded with so many features and automated behaviors that they have become complicated to actually use. While such "smart" capabilities can better support users' goals, the task of learning the "ins and outs" of different devices is daunting. Voice assistants aim to solve this problem by providing a natural language interface to devices, yet such assistants cannot understand loosely-constrained commands, they lack the ability to reason about and explain devices' behaviors to users, and they rely on connectivity to intrusive cloud infrastructure. Toward addressing these issues, we propose thoughtful things: devices that leverage lightweight, on-device language models to take actions and explain their behaviors in response to unconstrained user commands. We propose an end-to-end framework that leverages formal modeling, automated training data synthesis, and generative language models to create devices that are both capable and thoughtful in the presence of unconstrained user goals and inquiries. Our framework requires no labeled data and can be deployed on-device, with no cloud dependency. We implement two thoughtful things (a lamp and a thermostat) and deploy them on real hardware, evaluating their practical performance.