From Role-Play to Drama-Interaction: An LLM Solution
This work addresses the challenge of limited drama resources and uncontrollable narrative development for creators and users of interactive storytelling, though it appears incremental as it builds on existing LLM techniques for a specific domain.
The paper tackles the problem of creating interactive drama with large language models (LLMs) to enhance immersion by allowing user interaction with characters and scenes, resulting in a proposed pipeline with methods like Narrative Chain and Auto-Drama that are evaluated on manually crafted scripts such as Detective Conan and Harry Potter.
Drama is a form of storytelling inspired by human creativity, proceeding with a predefined storyline, carrying emotions and thoughts. This paper introduces \emph{LLM-based interactive drama}, which endows traditional drama with an unprecedented immersion, where a person is allowed to walk into it and interact with the characters and scenes. We define this new artistic genre by 6 essential elements-plot, character, thought, diction, spectacle and interaction-and study the entire pipeline to forge a backbone \emph{drama LLM} to drive the playing process, which is challenged by limited drama resources, uncontrollable narrative development, and complicated instruction following. We propose \emph{Narrative Chain} to offer finer control over the narrative progression during interaction with players; \emph{Auto-Drama} to synthesize drama scripts given arbitrary stories; \emph{Sparse Instruction Tuning} to allow the model to follow sophisticated instructions. We manually craft 3 scripts, \emph{Detective Conan}, \emph{Harry Potter}, \emph{Romeo and Juliet}, and design a 5-dimension principle to evaluate the drama LLM comprehensively.