# Ex3: Automatic Novel Writing by Extracting, Excelsior and Expanding

arXiv: https://arxiv.org/abs/2408.08506 · HTML: https://mlsanity.com/paper/2408.08506/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 40 references that are in the map.
- First posted on arXiv 16 Aug 2024.

## Builds on (most cited first, 18 of 18)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [Plan-And-Write: Towards Better Automatic Storytelling](https://mlsanity.com/paper/1811.05701/) (2018)
- [Re3: Generating Longer Stories With Recursive Reprompting and Revision](https://mlsanity.com/paper/2210.06774/) (2022)
- [Blockwise Self-Attention for Long Document Understanding](https://mlsanity.com/paper/1911.02972/) (2019)
- [Unlimiformer: Long-Range Transformers with Unlimited Length Input](https://mlsanity.com/paper/2305.01625/) (2023)
- [Strategies for Structuring Story Generation](https://mlsanity.com/paper/1902.01109/) (2019)
- [Learning to Encode Position for Transformer with Continuous Dynamical Model](https://mlsanity.com/paper/2003.09229/) (2020)
- [A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation](https://mlsanity.com/paper/1808.06945/) (2018)
- [R-Transformer: Recurrent Neural Network Enhanced Transformer](https://mlsanity.com/paper/1907.05572/) (2019)
- [Summarize, Outline, and Elaborate: Long-Text Generation via Hierarchical Supervision from Extractive Summaries](https://mlsanity.com/paper/2010.07074/) (2020)
- [Go Back in Time: Generating Flashbacks in Stories with Event Temporal Prompts](https://mlsanity.com/paper/2205.01898/) (2022)

## Built on by (most cited first, 10 of 10)

- [WritingBench: A Comprehensive Benchmark for Generative Writing](https://mlsanity.com/paper/2503.05244/) (2025)
- [R2: A LLM Based Novel-to-Screenplay Generation Framework with Causal Plot Graphs](https://mlsanity.com/paper/2503.15655/) (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)
- [DTBench: A Synthetic Benchmark for Document-to-Table Extraction](https://mlsanity.com/paper/2602.13812/) (2026)
- [Long Story Generation via Knowledge Graph and Literary Theory](https://mlsanity.com/paper/2508.03137/) (2025)
- [Beyond Direct Generation: A Decomposed Approach to Well-Crafted Screenwriting with LLMs](https://mlsanity.com/paper/2510.23163/) (2025)
- [CreAgentive: An Agent Workflow Driven Multi-Category Creative Generation Engine](https://mlsanity.com/paper/2509.26461/) (2025)
- [LLMs Should Incorporate Explicit Mechanisms for Human Empathy](https://mlsanity.com/paper/2604.10557/) (2026)
- [When to Plan, When to Polish: Noise Level as a Granularity Axis for Diffusion Language Models](https://mlsanity.com/paper/2606.21802/) (2026)
- [Scaling Long-Form Story Generation via Narrative State Tracking](https://mlsanity.com/paper/2609.35759/) (2026)

## Abstract (arXiv)

Generating long-term texts such as novels using artificial intelligence has always been a challenge. A common approach is to use large language models (LLMs) to construct a hierarchical framework that first plans and then writes. Despite the fact that the generated novels reach a sufficient length, they exhibit poor logical coherence and appeal in their plots and deficiencies in character and event depiction, ultimately compromising the overall narrative quality. In this paper, we propose a method named Extracting Excelsior and Expanding. Ex3 initially extracts structure information from raw novel data. By combining this structure information with the novel data, an instruction-following dataset is meticulously crafted. This dataset is then utilized to fine-tune the LLM, aiming for excelsior generation performance. In the final stage, a tree-like expansion method is deployed to facilitate the generation of arbitrarily long novels. Evaluation against previous methods showcases Ex3's ability to produce higher-quality long-form novels.