Published as a conference paper at ICLR 2025R 2: A LLM B ASED N OVEL-TO-S CREENPLAYG ENER-ATIONF RAMEWORK WITH C AUSALP LOT G RAPHS Zefeng Lin 1, Yi Xiao 1, Zhiqiang Mo 1, Qifan Zhang 1, Jie Wang 2, Jiayang Chen 2, Jiajing Zhang 2, Hui Zhang 1, Zhengyi Liu 3, Xianyong Fang 3, Xiaohua Xu 1 1 University of Science and Technology of China 2 Anhui Jianzhu University 3 Anhui University A BSTRACT Automatically adapting novels into screenplays is important for the TV, film, or opera industries to promote products with low costs. The strong performances of large language models (LLMs) in long-text generation call us to propose a LLM based framework Reader-Rewriter (R 2) for this task. However, there are two fundamental challenges here. First, the LLM hallucinations may cause inconsistent plot extraction and screenplay generation. Second, the causality-embedded plot lines should be effectively extracted for coherent rewriting. Therefore, two corresponding tactics are proposed: 1) A hallucination-aware refinement method (HAR) to iteratively discover and eliminate the affections of hallucinations; and 2) a causal plot-graph construction method (CPC) based on a greedy cycle-breaking algorithm to efficiently construct plot lines with event causalities. Recruiting those efficient techniques, R 2 utilizes two modules to mimic the human screenplay rewriting process: The Reader module adopts a sliding window and CPC to build the causal plot graphs, while the Rewriter module generates first the scene outlines based on the graphs and then the screenplays. HAR is integrated into both modules for accurate inferences of LLMs.

Multiple new programs and services are now advertising that AI can be used to write screenplays and automate the filmmaking process. For instance, the AI startup Deepmind recently announced the launch of a tool called Dramatron, what it calls a "co-writing" tool. According to its website, Dramatron is supposed to help screenwriters by using "hierarchical story generation for consistency across the generated text. Starting from a log line, Dramatron interactively generates character descriptions, plot points, location descriptions and dialogue..." This offends me on so many different levels that I can't really even begin to unpack them. I mean, why even write the script at all?

It seems that artificial intelligence has been taking over the creative world, where we have seen for weeks how people have been making use of this technology to generate images in different styles. Now it looks like the AI might even be able to help you create the script for that movie or play that has been on your mind for a long time. That's right, all thanks to the work done by the team at Alphabet DeepMindwhich resulted in Dramatron, an AI tool that performs its functions as a co-writer by helping you with tasks such as generate descriptions of characters, as well as places and dialoguesalso including plot points. Once the text is generated by this AI tool, it will be the turn of the human writer to compile, edit and rewrite the material to fit their vision. To take advantage of Dramatron you will first need a openai api key.

Have you ever thought up an idea for a movie or play that you just know will be a smash hit, but haven't gotten around to writing the script? Alphabet's DeepMind has built an AI tool that can help get you started. Dramatron is a so-called "co-writing" tool that can generate character descriptions, plot points, location descriptions and dialogue. The idea is that human writers will be able to compile, edit and rewrite what Dramatron comes up with into a proper script. Think of it like ChatGPT, but with output that you can edit into a blockbuster movie script.

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 critical reflections both from our interviewees and from independent reviewers who watched stagings of the works 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.