Designing and Evaluating Dialogue LLMs for Co-Creative Improvised Theatre

arXiv:2405.07111v1 Announce Type: new
Abstract: Social robotics researchers are increasingly interested in multi-party trained conversational agents. With a growing demand for real-world evaluations, our study presents Large Language Models (LLMs) deployed in a month-long live show at the Edinburgh Festival Fringe. This case study investigates human improvisers co-creating with conversational agents in a professional theatre setting. We explore the technical capabilities and constraints of on-the-spot multi-party dialogue, providing comprehensive insights from both audience and performer experiences with AI on stage. …

abstract agents arxiv case case study conversational conversational agents creative cs.cl demand designing dialogue edinburgh festival human language language models large language large language models llms researchers robotics show social study theatre type world