# R2: A LLM Based Novel-to-Screenplay Generation Framework with Causal Plot Graphs

arXiv: https://arxiv.org/abs/2503.15655 · HTML: https://mlsanity.com/paper/2503.15655/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 27 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Self-critiquing models for assisting human evaluators](https://mlsanity.com/paper/2206.05802/) (2022)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://mlsanity.com/paper/2302.12813/) (2023)
- [Re3: Generating Longer Stories With Recursive Reprompting and Revision](https://mlsanity.com/paper/2210.06774/) (2022)
- [Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionals](https://mlsanity.com/paper/2209.14958/) (2022)
- [Training Language Models with Language Feedback at Scale](https://mlsanity.com/paper/2303.16755/) (2023)
- [MovieFactory: Automatic Movie Creation from Text using Large Generative Models for Language and Images](https://mlsanity.com/paper/2306.07257/) (2023)
- [IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script Generation](https://mlsanity.com/paper/2407.01093/) (2024)
- [Creativity Support in the Age of Large Language Models: An Empirical Study Involving Emerging Writers](https://mlsanity.com/paper/2309.12570/) (2023)
- [Ex3: Automatic Novel Writing by Extracting, Excelsior and Expanding](https://mlsanity.com/paper/2408.08506/) (2024)
- [StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models](https://mlsanity.com/paper/2409.10132/) (2024)

## Built on by (most cited first, 5 of 5)

- [CML-Bench: A Framework for Evaluating and Enhancing LLM-Powered Movie Scripts Generation](https://mlsanity.com/paper/2510.06231/) (2025)
- [Plug-and-Play Dramaturge: A Divide-and-Conquer Approach for Iterative Narrative Script Refinement via Collaborative LLM Agents](https://mlsanity.com/paper/2510.05188/) (2025)
- [Beyond Direct Generation: A Decomposed Approach to Well-Crafted Screenwriting with LLMs](https://mlsanity.com/paper/2510.23163/) (2025)
- [Planning Beyond Text: Graph-based Reasoning for Complex Narrative Generation](https://mlsanity.com/paper/2604.21253/) (2026)
- [Position: Natural Language Should Not Fully Replace Formal Languages](https://mlsanity.com/paper/2607.20432/) (2026)

## Abstract (arXiv)

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 (R2) 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, R2 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. Experimental results demonstrate the superiority of R2, which substantially outperforms three existing approaches (51.3%, 22.6%, and 57.1% absolute increases) in pairwise comparison at the overall win rate for GPT-4o.