LongStory: Coherent, Complete and Length Controlled Long story Generation
Not on the map. Why?
Abstract (arXiv)
A human author can write any length of story without losing coherence. Also, they always bring the story to a proper ending, an ability that current language models lack. In this work, we present the LongStory for coherent, complete, and length-controlled long story generation. LongStory introduces two novel methodologies: (1) the long and short-term contexts weight calibrator (CWC) and (2) long story structural positions (LSP). The CWC adjusts weights for long-term context Memory and short-term context Cheating, acknowledging their distinct roles. The LSP employs discourse tokens to convey the structural positions of a long story. Trained on three datasets with varied average story lengths, LongStory outperforms other baselines, including the strong story generator Plotmachine, in coherence, completeness, relevance, and repetitiveness. We also perform zero-shot tests on each dataset to assess the model's ability to predict outcomes beyond its training data and validate our methodology by comparing its performance with variants of our model.
Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 33 of its 39 references that are in the map. First posted on arXiv 26 Nov 2023.
Builds on
33 of 39 references.
References · 33
- 2017Attention Is All You Needcited by 60,361
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
- 2020Longformer: The Long-Document Transformercited by 3,413
- 2018Hierarchical Neural Story Generationcited by 1,193
- 2019Defending Against Neural Fake Newscited by 559
- 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 376
- 2018Plan-And-Write: Towards Better Automatic Storytellingcited by 234
- 2022Re3: Generating Longer Stories With Recursive Reprompting and Revisioncited by 193
21 more
- 2021BookSum: A Collection of Datasets for Long-form Narrative Summarizationcited by 184
- 2019Strategies for Structuring Story Generationcited by 124
- 2021How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVENcited by 124
- 2020A Knowledge-Enhanced Pretraining Model for Commonsense Story Generationcited by 116
- 2019Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systemscited by 110
- 2020PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Trackingcited by 105
- 2022Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generationcited by 75
- 2020Consistency of a Recurrent Language Model With Respect to Incomplete Decodingcited by 54
- 2018Controllable Neural Story Plot Generation via Reward Shapingcited by 49
- 2021Long Text Generation by Modeling Sentence-Level and Discourse-Level Coherencecited by 45
- 2022PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generationcited by 30
- 2021Inferring the Reader: Guiding Automated Story Generation with Commonsense Reasoningcited by 29
- 2021Automatic Story Generation: Challenges and Attemptscited by 28
- 2021proScript: Partially Ordered Scripts Generation via Pre-trained Language Modelscited by 21
- 2020Narrative Interpolation for Generating and Understanding Storiescited by 19
- 2021Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codescited by 19
- 2021GraphPlan: Story Generation by Planning with Event Graphcited by 18
- 2022EtriCA: Event-Triggered Context-Aware Story Generation Augmented by Cross Attentioncited by 17
- 2020Progressive Generation of Long Text with Pretrained Language Modelscited by 14
- 2021Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learningcited by 14
- 2019Fiction Sentence Expansion and Enhancement via Focused Objective and Novelty Curve Samplingcited by 4
Built on by
Citing papers per year: 2024: 4; 2025: 4; 2026: 4.
12 papers.
- 2024What Makes a Good Story and How Can We Measure It? A Comprehensive Survey of Story Evaluationcited by 17
- 2024A Character-Centric Creative Story Generation via Imaginationcited by 12
- 2025Avoidance Decoding for Diverse Multi-Branch Story Generationcited by 6
- 2024GPT-Powered Elicitation Interview Script Generator for Requirements Engineering Trainingcited by 3
- 2025MultiActor-Audiobook: Zero-Shot Audiobook Generation with Faces and Voices of Multiple Speakerscited by 2
- 2024Explaining Mixtures of Sources in News Articlescited by 1
- 2025FlexMUSE: Multimodal Unification and Semantics Enhancement Framework with Flexible interaction for Creative Writingcited by 1
- 2026A Universal Avoidance Method for Diverse Multi-branch Generationcited by 1
- 2025CreAgentive: An Agent Workflow Driven Multi-Category Creative Generation Enginecited by 0
- 2026LitVISTA: A Benchmark for Narrative Orchestration in Literary Textcited by 0
- 2026ConWriter: Transition-Constrained Stateful Long-Form Story Generation with Lightweight Neuro-Symbolic Consistency Controlcited by 0
- 2026StorySpark: Module-wise Evolutionary Search for Story Premise Generationcited by 0
- 2026StorySpark: Module-wise Evolutionary Search for Story Premise Generation3 Jun 2026
- 2026ConWriter: Transition-Constrained Stateful Long-Form Story Generation with Lightweight Neuro-Symbolic Consistency Control27 May 2026
- 2026A Universal Avoidance Method for Diverse Multi-branch Generation19 Apr 2026
- 2026LitVISTA: A Benchmark for Narrative Orchestration in Literary Text10 Jan 2026
- 2025CreAgentive: An Agent Workflow Driven Multi-Category Creative Generation Engine30 Sep 2025
- 2025Avoidance Decoding for Diverse Multi-Branch Story Generation2 Sep 2025
- 2025FlexMUSE: Multimodal Unification and Semantics Enhancement Framework with Flexible interaction for Creative Writing22 Aug 2025
- 2025MultiActor-Audiobook: Zero-Shot Audiobook Generation with Faces and Voices of Multiple Speakers19 May 2025
- 2024Explaining Mixtures of Sources in News Articles7 Nov 2024
- 2024A Character-Centric Creative Story Generation via Imagination25 Sep 2024
- 2024What Makes a Good Story and How Can We Measure It? A Comprehensive Survey of Story Evaluation26 Aug 2024
- 2024GPT-Powered Elicitation Interview Script Generator for Requirements Engineering Training17 Jun 2024