PAYADOR: A Minimalist Approach to Grounding Language Models on Structured Data for Interactive Storytelling and Role-playing Games
This addresses the constraint on player free will in improvisation-focused RPGs, offering a novel approach to enhance co-creativity.
The paper tackles the world-update problem in Interactive Storytelling and Role-playing Games by predicting action outcomes instead of mapping inputs to preprogrammed actions, using a Large Language Model grounded on a minimal world representation to achieve promising results.
Every time an Interactive Storytelling (IS) system gets a player input, it is facing the world-update problem. Classical approaches to this problem consist in mapping that input to known preprogrammed actions, what can severely constrain the free will of the player. When the expected experience has a strong focus on improvisation, like in Role-playing Games (RPGs), this problem is critical. In this paper we present PAYADOR, a different approach that focuses on predicting the outcomes of the actions instead of representing the actions themselves. To implement this approach, we ground a Large Language Model to a minimal representation of the fictional world, obtaining promising results. We make this contribution open-source, so it can be adapted and used for other related research on unleashing the co-creativity power of RPGs.