An Evaluation of LLM-based Chatbots for Enhancing the Visitor’s User Experience at Cultural Exhibits

Museums are increasingly integrating advanced technologies to offer new experiences to visitors. Among these, generative AI, particularly Large Language Models (LLMs), is gaining prominence in the cultural heritage sector. This paper evaluates a system that leverages LLMs for content creation and personalized museum recommendations. To assess the impact of this technology on User Experience (UX) and audience engagement, three case studies were conducted across a digital art exhibition, a painting gallery, and an archaeological museum. The LLM-based chatbots were customized for each context, providing tailored interactions for visitors. A mixed-method approach, combining quantitative visitor questionnaires with qualitative semi-structured interviews, was employed to gather comprehensive feedback. The results indicate that LLMs have significant potential to enhance visitor engagement and deliver personalized experiences, contributing to more meaningful interactions in cultural spaces. While challenges remain, particularly in context-awareness, the study highlights the promising role of AI in enriching museum environments as these technologies continue to evolve.