HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing
This addresses the problem of limited creativity in LLMs for expert-level writing tasks like screenwriting, offering a domain-specific solution.
The paper tackles the challenge of generating high-quality screenplays with large language models (LLMs) by proposing HoLLMwood, a framework that assigns LLMs to roles like Writer, Editor, and Actors to mimic human creative processes, resulting in substantial improvements in coherence, relevance, interestingness, and overall quality over strong baselines.
Generative AI has demonstrated unprecedented creativity in the field of computer vision, yet such phenomena have not been observed in natural language processing. In particular, large language models (LLMs) can hardly produce written works at the level of human experts due to the extremely high complexity of literature writing. In this paper, we present HoLLMwood, an automated framework for unleashing the creativity of LLMs and exploring their potential in screenwriting, which is a highly demanding task. Mimicking the human creative process, we assign LLMs to different roles involved in the real-world scenario. In addition to the common practice of treating LLMs as ${Writer}$, we also apply LLMs as ${Editor}$, who is responsible for providing feedback and revision advice to ${Writer}$. Besides, to enrich the characters and deepen the plots, we introduce a role-playing mechanism and adopt LLMs as ${Actors}$ that can communicate and interact with each other. Evaluations on automatically generated screenplays show that HoLLMwood substantially outperforms strong baselines in terms of coherence, relevance, interestingness and overall quality.