DOCSEARCHbyAlgolia
Submit Docs

Awesome Story Generation

repository·main·Indexed 20 days ago

https://github.com/yingpengma/awesome-story-generation

A curated resource repository of research papers and datasets focused on LLM-based story generation and storytelling techniques. The collection categorizes research across dimensions including planning, multi-agent systems, multimodality, controllable and personalized generation, and story evaluation.

Tokens
5.9K
Snippets
0
Records
26
Agent score
21%

What's inside awesome-story-generation

  1. Introduction to Awesome-Story-Generation

    main

    The awesome-story-generation repository is a curated collection of research papers focused on Story Generation and Storytelling, with a primary emphasis on techniques utilizing Large Language Models (LLMs).

    Papers are organized in chronological order, with the most recent research appearing at the top of the list. The collection is categorized into several key research areas:

    • Large Language Models
    • Plot Development
    • Better Storytelling
    • Story Character
    • Writing Style
    • Story Planning
    • Controllable Story
    • Reasonable Story
    • Benchmarks

  2. Overview of Awesome-Story-Generation

    main

    Awesome-Story-Generation is a curated collection of research papers focused on Story Generation and Storytelling within the era of Large Language Models (LLMs). The repository organizes research chronologically (most recent first) across several key dimensions of story generation, including planning, multi-agent systems, multimodality, and evaluation.

    Note: This repository focuses exclusively on LLM-related research. For research conducted prior to the LLM era, refer to the Old Version, which is no longer maintained.

  3. Research papers on Story Generation Overview

    main

    A collection of survey papers and foundational research regarding story generation, including:

    • What Makes a Good Story and How Can We Measure It? A Comprehensive Survey of Story Evaluation (ArXiv-2024)
    • The Value, Benefits, and Concerns of Generative AI-Powered Assistance in Writing (CHI-2024)
    • Weaver: Foundation Models for Creative Writing (ArXiv-2024)
    • Open-world Story Generation with Structured Knowledge Enhancement: A Comprehensive Survey (Neurocomputing-2023)
    • Are NLP Models Good at Tracing Thoughts: An Overview of Narrative Understanding (EMNLP Findings-2023)

  5. Research papers on Better Storytelling techniques

    main

    Papers focusing on improving story quality through emotional arcs, pacing, RAG, and coherence:

    • All Stories Are One Story: Emotional Arc Guided Procedural Game Level Generation (ArXiv-2025)
    • Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole Detection (ArXiv-2025)
    • Learning to Reason for Long-Form Story Generation (ArXiv-2025)
    • MLD-EA: Check and Complete Narrative Coherence by Introducing Emotions and Actions (ArXiv-2024)
    • SWAG: Storytelling With Action Guidance (EMNLP Findings-2024)
    • Improving Pacing in Long-Form Story Planning (EMNLP Findings-2023)
    • End-to-End Story Plot Generator (ArXiv-2023)
    • GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidence (EMNLP Findings-2023)

  6. Research papers on Story Evaluation

    main

    Papers covering metrics, benchmarks, and automated evaluation of stories:

    • Re:Verse -- Can Your VLM Read a Manga? (ICCV AISTORY Workshop-2025)
    • CoKe: Customizable Fine-Grained Story Evaluation via Chain-of-Keyword Rationalization (ArXiv-2025)
    • LongEval: A Comprehensive Analysis of Long-Text Generation Through a Plan-based Paradigm (ArXiv-2025)
    • Echoes in AI: Quantifying Lack of Plot Diversity in LLM Outputs (ArXiv-2025)
    • Evaluating Creative Short Story Generation in Humans and Large Language Models (ArXiv-2024)
    • CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints (ArXiv-2024)
    • Small Language Models can Outperform Humans in Short Creative Writing: A Study Comparing SLMs with Humans and LLMs (COLING-2025)
    • FACTTRACK: Time-Aware World State Tracking in Story Outlines (NAACL-2025)
    • Are Large Language Models Capable of Generating Human-Level Narratives? (EMNLP-2024)
    • STORYSUMM: Evaluating Faithfulness in Story Summarization (EMNLP-2024)
    • Pron vs Prompt: Can Large Language Models already Challenge a World-Class Fiction Author at Creative Text Writing? (ArXiv-2024)
    • Measuring Psychological Depth in Language Models (EMNLP-2024)
    • Do Language Models Enjoy Their Own Stories? Prompting Large Language Models for Automatic Story Evaluation (TACL-2024)
    • Reading Subtext: Evaluating Large Language Models on Short Story Summarization with Writers (TACL-2024)
    • A Confederacy of Models: a Comprehensive Evaluation of LLMs on Creative Writing (EMNLP Findings-2023)
    • Learning Personalized Alignment for Evaluating Open-ended Text Generation (EMNLP-2024)
    • BooookScore: A systematic exploration of book-length summarization in the era of LLMs (ICLR-2024)
    • TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks (TMLR-2024)
    • Art or Artifice? Large Language Models and the False Promise of Creativity (CHI-2023)
    • HAUSER: Towards Holistic and Automatic Evaluation of Simile Generation (ACL-2023)
    • Can Large Language Models Be an Alternative to Human Evaluations? (ACL-2023)
    • DeltaScore: Evaluating Story Generation with Differentiating Perturbations (EMNLP Findings-2023)
    • StoryER: Automatic Story Evaluation via Ranking, Rating and Reasoning (EMNLP-2022)
    • Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation (COLING-2022)
    • LOT: A story-centric benchmark for evaluating Chinese long text understanding and generation (TACL-2022)
    • Openmeva: A benchmark for evaluating open-ended story generation metrics (ACL-2021)
    • Union: An unreferenced metric for evaluating open-ended story generation (EMNLP-2020)

  7. Research papers on Writing Style and Author-Style Transfer

    main

    This collection of research papers focuses on controlling and transferring writing styles in story generation.

    Key research areas include:

    • Pastiche & Fan Fiction: Generating content in a specific favorite author's style.
    • Author Style Inference: Personalizing story generation by inferring the author's style.
    • Style Transfer: Techniques for non-parallel story author-style transfer and Chinese article-style transfer.
    • Arbitrary Style Generation: Learning to generate text in various writing styles.
    • Style-Guided Planning: Using planning to achieve stylized story generation.

  8. Research papers for Controllable Story Generation

    main

    This section provides a curated list of research papers focused on making story generation more controllable. Key research areas include:

    • Modular Premise Synthesis: Using modular approaches for open-ended generation (e.g., MoPS).
    • Endpoint-based Generation: Generating narratives that return to specific starting or ending points.
    • Fine-grained Control: Using control codes (e.g., LiFi) or controlling specific keywords and their positions.
    • Psychological and Genre Control: Guiding generation via psychological principles or specific genres.
    • Plug-and-Play Methods: Frameworks that allow for controlled generation without extensive retraining (e.g., k2t, Plug-and-Blend).
    • Variational Autoencoders (VAE): Using Transformer-based CVAEs for controllable generation.
    • Outline-to-Story: Generating stories from cascaded event outlines.
    • Sentiment and Reward Shaping: Controlling story endings via sentiment or using reward shaping for plot generation.

  9. Research papers on Controllable story generation

    main

    Papers exploring methods to control story generation via coherence, genre, style, or specific endpoints:

    • SCORE: Story Coherence and Retrieval Enhancement for AI Narratives (ArXiv-2025)
    • NarrativeGenie: Generating Narrative Beats and Dynamic Storytelling with Large Language Models (AIIDE-2024)
    • Crafting Narrative Closures: Zero-Shot Learning with SSM Mamba for Short Story Ending Generation (ArXiv-2024)
    • MoPS: Modular Story Premise Synthesis for Open-Ended Automatic Story Generation (ACL-2024)
    • Multigenre AI-powered Story Composition (ArXiv-2024)
    • Returning to the Start: Generating Narratives with Related Endpoints (NAACL-2024)
    • With Greater Text Comes Greater Necessity: Inference-Time Training Helps Long Text Generation (COLM-2024)
    • RLCD: Reinforcement Learning from Contrast Distillation for Language Model Alignment (ICLR-2024)
    • RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text (ArXiv-2023)

  10. Research papers for Plot Development in story generation

    main

    Papers exploring techniques for generating, predicting, and expanding story plots, including end-to-end generators and structured knowledge approaches.

    Key papers include:

    • Stanford CS224N Custom Project-2023: Novelty: Optimizing StreamingLLM for Novel Plot Generation
    • ArXiv-2023: End-to-End Story Plot Generator
    • AAAI Workshop-2023: Conveying the Predicted Future to Users: A Case Study of Story Plot Prediction
    • RANLP-2023: Coherent Story Generation with Structured Knowledge
    • EMNLP-2022: EtriCA: Event-triggered context-aware story generation augmented by cross attention
    • INLG-2022: Plot Writing From Pre-Trained Language Models
    • AAAI-2020: Story Realization: Expanding Plot Events into Sentences (includes code)

  12. Reference datasets for story generation

    main

    The following datasets are curated for research in collaborative story generation, authorship analysis, and narrative understanding:

    • CollabStory: Multi-LLM collaborative story generation and authorship analysis (ArXiv-2024).
    • Reflections & Resonance: Two-agent partnership for LLM-based story annotation (IREC-COLING-2024).
    • CMDAG: Chinese Metaphor Dataset with annotated grounds as CoT for boosting metaphor generation (ArXiv-2024).
    • STONYBOOK: System and resource for large-scale analysis of novels (ArXiv-2023).
    • StoryWars: Dataset and instruction tuning baselines for collaborative story understanding and generation (ACL-2023).
    • PASTA: Dataset for modeling participant states in narratives (TACL-2023).
    • Moral Stories Corpus: Corpus for understanding and generating moral stories (NAACL-2022).
    • StoryDB: Broad multi-language narrative dataset (EVAL4NLP-2021).
    • SummScreen: Dataset for abstractive screenplay summarization (ACL-2022). Includes data.
    • TVStoryGen: Dataset for generating stories with character descriptions (Arxiv-2021).
    • STORIUM: Dataset and evaluation platform for machine-in-the-loop story generation (EMNLP-2020).