Saved in:
Bibliographic Details
Main Authors: Góngora, Santiago, Chiruzzo, Luis, Méndez, Gonzalo, Gervás, Pablo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.07304
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910908227256320
author Góngora, Santiago
Chiruzzo, Luis
Méndez, Gonzalo
Gervás, Pablo
author_facet Góngora, Santiago
Chiruzzo, Luis
Méndez, Gonzalo
Gervás, Pablo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_07304
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PAYADOR: A Minimalist Approach to Grounding Language Models on Structured Data for Interactive Storytelling and Role-playing Games
Góngora, Santiago
Chiruzzo, Luis
Méndez, Gonzalo
Gervás, Pablo
Computation and Language
Artificial Intelligence
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.
title PAYADOR: A Minimalist Approach to Grounding Language Models on Structured Data for Interactive Storytelling and Role-playing Games
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2504.07304