LLM-mediated domain-specific voice agents
The case of TextileBot
Bibliographic Data
| ID | 21452243 |
|---|---|
| Authors | Shu Zhong (0000-0002-1820-6424, University College London, corresponding author), Elia Gatti (0009-0008-1675-1323, University College London), James Hardwick (University College London), Miriam Ribul (0000-0002-0323-9020, Royal College of Art), Youngjun Cho (0000-0001-5695-0759, University College London), Marianna Obrist (0000-0002-4009-1627, University College London) |
| Year | 2025 |
| Pages | 1-33 |
| Publication date | 2025-02-03 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Behaviour and Information Technology (JOURNAL) |
| Journal identifiers | ISSN: 0144-929X • E-ISSN: 1362-3001 |
| Publisher | Informa UK Limited (PUBLISHER • GB) |
| DOI | 10.1080/0144929x.2025.2456667 |
| OpenAlex | W4407100023 |
| Language | EN |
| Citations received | 3 |
| References cited | 80 |
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
Domain (mathematical analysis) · Speech recognition · Communication · Computer Science · Mathematics · Natural Language Processing Techniques · Psychology · Speech and dialogue systems · Topic Modeling
Doing Conversation Analysis
Mixed effects models and extensions in ecology with R
Conversational Style
The Cambridge Handbook of Linguistic Code-switching
Conversational agents in healthcare
Interaction Analysis
Models in information behaviour research
Pre-train, Prompt, and Predict
On differences between spoken and written language∗
The Predictability of Informal Conversation
| Citations per year | 3 |
|---|---|
| Citation span | 2025 - 2026 (2) |
| Highly cited | No |