ReactGenie: A Development Framework for Complex Multimodal Interactions Using Large Language Models

TL;DR

ReactGenie is a framework that simplifies the development of complex multimodal interfaces by translating user commands into a specialized programming language, enabling richer interactions and faster task completion.

Contribution

It introduces NLPL and a neural semantic parser to separate multimodal input from the computational model, easing development of advanced multimodal applications.

Findings

Developers learned to build applications in under 2.5 hours.

Users completed tasks faster with ReactGenie.

ReactGenie supports richer multimodal commands.

Abstract

By combining voice and touch interactions, multimodal interfaces can surpass the efficiency of either modality alone. Traditional multimodal frameworks require laborious developer work to support rich multimodal commands where the user's multimodal command involves possibly exponential combinations of actions/function invocations. This paper presents ReactGenie, a programming framework that better separates multimodal input from the computational model to enable developers to create efficient and capable multimodal interfaces with ease. ReactGenie translates multimodal user commands into NLPL (Natural Language Programming Language), a programming language we created, using a neural semantic parser based on large-language models. The ReactGenie runtime interprets the parsed NLPL and composes primitives in the computational model to implement complex user commands. As a result, ReactGenie allows easy implementation and unprecedented richness in commands for end-users of multimodal apps. Our evaluation showed that 12 developers can learn and build a nontrivial ReactGenie application in under 2.5 hours on average. In addition, compared with a traditional GUI, end-users can complete tasks faster and with less task load using ReactGenie apps.