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

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.

Published at Behaviour and Information Technology Journal

References in corpus (23)

• Training language models to follow instructions with human feedback
• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• LoRA: Low-Rank Adaptation of Large Language Models
• On the Opportunities and Risks of Foundation Models
• Robust Speech Recognition via Large-Scale Weak Supervision
• Large Language Models are Zero-Shot Reasoners
• Tree of Thoughts: Deliberate Problem Solving with Large Language Models
• Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
• Graph of Thoughts: Solving Elaborate Problems with Large Language Models
• What Makes a Good Conversation? Challenges in Designing Truly Conversational Agents
• KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction
• CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities
• Challenges and Applications of Large Language Models
• Holistic Evaluation of Language Models
• The Impact of Multiple Parallel Phrase Suggestions on Email Input and Composition Behaviour of Native and Non-Native English Writers
• Eliciting and Analysing Users' Envisioned Dialogues with Perfect Voice Assistants
• Ask Me Anything: A simple strategy for prompting language models
• Evaluating Human-Language Model Interaction
• Creative Writing with an AI-Powered Writing Assistant: Perspectives from Professional Writers
• Scaling Laws for Reward Model Overoptimization
• A Mixed-Methods Approach to Understanding User Trust after Voice Assistant Failures
• Can You be More Social? Injecting Politeness and Positivity into Task-Oriented Conversational Agents
• TextileNet: A Material Taxonomy-based Fashion Textile Dataset