How to Make Museums More Interactive? Case Study of Artistic Chatbot

2025-08-30

AI Summary

This study addresses the limited interactivity and weak informal learning support in cultural venues such as museums. We propose an end-to-end voice dialogue system integrating large language models (LLMs) with retrieval-augmented generation (RAG). Deployed for the first time in a real-world art exhibition, the system employs a customized knowledge base to power a voice-enabled question-answering agent, enabling visitors to freely query both exhibition-specific and out-of-domain topics through a closed-loop interaction: speech input → semantic understanding → content grounding → speech output. Evaluation shows that 60% of system responses are directly exhibition-relevant, significantly enhancing visitor engagement and contextualized learning. Key contributions include: (1) empirical validation of RAG-enhanced LLMs for open-domain cultural dialogue; (2) the first lightweight voice interaction paradigm tailored to physical art exhibitions; and (3) a reusable technical framework for intelligent, context-aware museum guidance systems.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Conversational AI/Dialog Systems
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Conversational agents powered by Large Language Models (LLMs) are increasingly utilized in educational settings, in particular in individual closed digital environments, yet their potential adoption in the physical learning environments like cultural heritage sites, museums, and art galleries remains relatively unexplored. In this study, we present Artistic Chatbot, a voice-to-voice RAG-powered chat system to support informal learning and enhance visitor engagement during a live art exhibition celebrating the 15th anniversary of the Faculty of Media Art at the Warsaw Academy of Fine Arts, Poland. The question answering (QA) chatbot responded to free-form spoken questions in Polish using the context retrieved from a curated, domain-specific knowledge base consisting of 226 documents provided by the organizers, including faculty information, art magazines, books, and journals. We describe the key aspects of the system architecture and user interaction design, as well as discuss the practical challenges associated with deploying chatbots at public cultural sites. Our findings, based on interaction analysis, demonstrate that chatbots such as Artistic Chatbot effectively maintain responses grounded in exhibition content (60% of responses directly relevant), even when faced with unpredictable queries outside the target domain, showing their potential for increasing interactivity in public cultural sites. GitHub project page: https://github.com/cinekucia/artistic-chatbot-cikm2025

Problem

• Enhancing museum interactivity through AI chatbots
• Addressing visitor engagement in physical cultural sites
• Grounding chatbot responses in domain-specific exhibition content

Innovation

• Voice-to-voice RAG-powered chat system
• Domain-specific knowledge base with 226 documents
• Free-form spoken question answering in Polish