UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

LLM-mediated domain-specific voice agents: the case of TextileBot

Zhong, Shu; Gatti, Elia; Hardwick, James; Ribul, Miriam; Cho, Youngjun; Obrist, Marianna; (2025) LLM-mediated domain-specific voice agents: the case of TextileBot. Behaviour and Information Technology 10.1080/0144929X.2025.2456667. (In press). Green open access

[thumbnail of LLM-mediated domain-specific voice agents  the case of TextileBot.pdf]
Preview
Text
LLM-mediated domain-specific voice agents the case of TextileBot.pdf - Published Version

Download (13MB) | Preview

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.

Type: Article
Title: LLM-mediated domain-specific voice agents: the case of TextileBot
Open access status: An open access version is available from UCL Discovery
DOI: 10.1080/0144929X.2025.2456667
Publisher version: https://doi.org/10.1080/0144929X.2025.2456667
Language: English
Additional information: © 2025 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. The terms on which this article has been published allow the posting of the Accepted Manuscript in a repository by the author(s) or with their consent.
Keywords: Human–AI interactions; domain-specific conversational agents; large language models; prompt engineering; voice agents; sustainability
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10204301
Downloads since deposit
2Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item