Co-Writing Screenplays and Theatre Scripts with Language Models: Evaluation by Industry Professionals
By Piotr Wojciech Mirowski, Kory Wallace Mathewson, Jaylen Pittman, Richard Evans. International Conference on Human Factors in Computing Systems, 2022
396 citations recorded by the source corpus.
Language models are increasingly attracting interest from writers. However, such models lack long-range semantic coherence, limiting their usefulness for longform creative writing. We address this limitation by applying language models hierarchically, in a system we call Dramatron. By building structural context via prompt chaining, Dramatron can generate coherent scripts and screenplays complete with title, characters, story beats, location descriptions, and dialogue. We illustrate Dramatron’s usefulness as an interactive co-creative system with a user study of 15 theatre and film industry professionals. Participants co-wrote theatre scripts and screenplays with Dramatron and engaged in open-ended interviews. We report reflections both from our interviewees and from independent reviewers who critiqued performances of several of the scripts to illustrate how both Dramatron and hierarchical text generation could be useful for human-machine co-creativity. Finally, we discuss the suitability of Dramatron for co-creativity, ethical considerations—including plagiarism and bias—and participatory models for the design and deployment of such tools.
Subfields: Control and Systems Engineering, Language and Linguistics
View Paper: https://www.semanticscholar.org/paper/f9b16559282e5bea0bb072f9e260a4f0af697f4a
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Language and Linguistics
Citations in the corpus
- When combinations of humans and AI are useful: A systematic review and meta-analysis (2024, neutral): “Much of the recent work on generative AI with human participants, however, tends to focus on attitudes towards the tool 44,45 , interviews or think-alouds with participants 46–48 , or user experience instead of task performance 49–51 .”
- Help me write a Poem - Instruction Tuning as a Vehicle for Collaborative Poetry Writing (2022, background): “Concurrent work has also shown that large language models can help users write scripts and screenplays (Mirowski et al., 2022) and longer stories (Yang et al., 2022) by generating text that incorporates structural context via prompt chaining.”
- Mind the Gap! Choice Independence in Using Multilingual LLMs for Persuasive Co-Writing Tasks in Different Languages (2025, unknown): “LLMs themselves have demonstrated exceptional performance in open-ended writing, with great potential benefit for a wide variety of tasks [51, 71, 78, 81, 83, 132, 139].”