LLM-Mediated Domain-Specific Voice Agents: The Case of TextileBot

TL;DR

This paper explores using prompt-enhanced Large Language Models to create domain-specific voice agents, demonstrated through TextileBot in textile circularity, with positive user engagement and insights into interaction dynamics.

Contribution

It introduces a novel prompt-based approach for developing domain-specific conversational agents without extensive data training, exemplified by TextileBot in the textile domain.

Findings

Participants engaged in multi-turn conversations with TextileBots.

Perceptions of different agent variations varied among users.

Prompt-based LLMs effectively supported domain-specific voice agents.

Abstract

Developing domain-specific conversational agents (CAs) has been challenged by the need for extensive domain-focused data. Recent advancements in Large Language Models (LLMs) make them a viable option as a knowledge backbone. LLMs behaviour can be enhanced through prompting, instructing them to perform downstream tasks in a zero-shot fashion (i.e. without training). To this end, we incorporated structural knowledge into prompts and used prompted LLMs to prototyping domain-specific CAs. We demonstrate a case study in a specific domain-textile circularity - TextileBot, we present the design, development, and evaluation of the TextileBot. Specially, we conducted an in-person user study (N=30) with Free Chat and Information-Gathering tasks with TextileBots to gather insights from the interaction. We analyse the human-agent interactions, combining quantitative and qualitative methods. Our results suggest that participants engaged in multi-turn conversations, and their perceptions of the three variation agents and respective interactions varied demonstrating the effectiveness of our prompt-based LLM approach. We discuss the dynamics of these interactions and their implications for designing future voice-based CAs.