Player-Driven Emergence in LLM-Driven Game Narrative
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917683550748672 |
|---|---|
| author | Peng, Xiangyu Quaye, Jessica Rao, Sudha Xu, Weijia Botchway, Portia Brockett, Chris Jojic, Nebojsa DesGarennes, Gabriel Lobb, Ken Xu, Michael Leandro, Jorge Jin, Claire Dolan, Bill |
| author_facet | Peng, Xiangyu Quaye, Jessica Rao, Sudha Xu, Weijia Botchway, Portia Brockett, Chris Jojic, Nebojsa DesGarennes, Gabriel Lobb, Ken Xu, Michael Leandro, Jorge Jin, Claire Dolan, Bill |
| contents | We explore how interaction with large language models (LLMs) can give rise to emergent behaviors, empowering players to participate in the evolution of game narratives. Our testbed is a text-adventure game in which players attempt to solve a mystery under a fixed narrative premise, but can freely interact with non-player characters generated by GPT-4, a large language model. We recruit 28 gamers to play the game and use GPT-4 to automatically convert the game logs into a node-graph representing the narrative in the player's gameplay. We find that through their interactions with the non-deterministic behavior of the LLM, players are able to discover interesting new emergent nodes that were not a part of the original narrative but have potential for being fun and engaging. Players that created the most emergent nodes tended to be those that often enjoy games that facilitate discovery, exploration and experimentation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_17027 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Player-Driven Emergence in LLM-Driven Game Narrative Peng, Xiangyu Quaye, Jessica Rao, Sudha Xu, Weijia Botchway, Portia Brockett, Chris Jojic, Nebojsa DesGarennes, Gabriel Lobb, Ken Xu, Michael Leandro, Jorge Jin, Claire Dolan, Bill Computation and Language Artificial Intelligence We explore how interaction with large language models (LLMs) can give rise to emergent behaviors, empowering players to participate in the evolution of game narratives. Our testbed is a text-adventure game in which players attempt to solve a mystery under a fixed narrative premise, but can freely interact with non-player characters generated by GPT-4, a large language model. We recruit 28 gamers to play the game and use GPT-4 to automatically convert the game logs into a node-graph representing the narrative in the player's gameplay. We find that through their interactions with the non-deterministic behavior of the LLM, players are able to discover interesting new emergent nodes that were not a part of the original narrative but have potential for being fun and engaging. Players that created the most emergent nodes tended to be those that often enjoy games that facilitate discovery, exploration and experimentation. |
| title | Player-Driven Emergence in LLM-Driven Game Narrative |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2404.17027 |