Voice CMS: updating the knowledge base of a digital assistant through conversation

TL;DR

This paper explores a voice-based multi-agent LLM system for updating digital assistant knowledge bases, comparing its usability and content quality to traditional graphical systems, and suggesting hybrid interfaces for optimal performance.

Contribution

It introduces a novel voice user interface for knowledge base updates using multi-agent LLMs and evaluates its effectiveness against traditional graphical systems.

Findings

VUI is preferred for simple tasks

Content quality is comparable across interfaces

Hybrid interfaces could improve usability and reduce cognitive load

Abstract

In this study, we propose a solution based on a multi-agent LLM architecture and a voice user interface (VUI) designed to update the knowledge base of a digital assistant. Its usability is evaluated in comparison to a more traditional graphical content management system (CMS), with a focus on understanding the relationship between user preferences and the complexity of the information being provided. The findings demonstrate that, while the overall usability of the VUI is rated lower than the graphical interface, it is already preferred by users for less complex tasks. Furthermore, the quality of content entered through the VUI is comparable to that achieved with the graphical interface, even for highly complex tasks. Obtained qualitative results suggest that a hybrid interface combining the strengths of both approaches could address the key challenges identified during the experiment, such as reducing cognitive load through graphical feedback while maintaining the intuitive nature of voice-based interactions. This work highlights the potential of conversational interfaces as a viable and effective method for knowledge management in specific business contexts.