mlsanityData to 14 Oct 2026

Measuring Information Distortion in Hierarchical Ultra long Novel Reconstruction:The Optimal Expansion Ratio

arXiv 2505.12572 ↗First posted 18 May 2025cs.CL cs.AI cs.ITcited by 0

Not on the map. Why?

Abstract (arXiv)

A two stage novel generation framework (outline -> section outline -> manuscript) is widely used in long novel generation,(e.g., textscDOME, textscPlan&Write, textscLong Writer), but study of such framework in ultra long novel(>1M words) reconstruction is little. Building on recent text compression methods (textscLLMZip, textscLLM2Vec), we conduct an information-theoretic analysis to quantify semantic distortion under different compression-expansion ratios. We examine how outline length affects information preservation. Experiments on ultra-long novels show that the optimal compression-expansion ratio significantly reduces semantic distortion compared to other non-optimal compression-expansion ratio.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 37 references that are in the map. First posted on arXiv 18 May 2025.

Builds on

21 of 37 references.

References · 21

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  3. 2024A Survey on LLM-as-a-Judgecited by 1,423
  4. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 578
  5. 2018Plan-And-Write: Towards Better Automatic Storytellingcited by 234
  6. 2022A Contrastive Framework for Neural Text Generationcited by 225
  7. 2019Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoffcited by 211
  8. 2023Generative artificial intelligence enhances creativity but reduces the diversity of novel contentcited by 167
  9. 2024LongLaMP: A Benchmark for Personalized Long-form Text Generationcited by 97
  10. 2021Pretrained Language Models for Text Generation: A Surveycited by 95
  11. 2023The Next Chapter: A Study of Large Language Models in Storytellingcited by 58
  12. 2021Long Text Generation by Modeling Sentence-Level and Discourse-Level Coherencecited by 45
9 more
  1. 2023GPT-who: An Information Density-based Machine-Generated Text Detectorcited by 40
  2. 2018DeepZip: Lossless Data Compression using Recurrent Neural Networkscited by 33
  3. 2024Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancementcited by 30
  4. 2024Language Models can Self-Lengthen to Generate Long Textscited by 24
  5. 2023Improving Pacing in Long-Form Story Planningcited by 21
  6. 2024Semantic Similarity Matching for Patent Documents Using Ensemble BERT-related Model and Novel Text Processing Methodcited by 18
  7. 2025LongEval: A Comprehensive Analysis of Long-Text Generation Through a Plan-based Paradigmcited by 14
  8. 2024How good is my story? Towards quantitative metrics for evaluating LLM-generated XAI narrativescited by 7
  9. 2023A Comparison of Document Similarity Algorithmscited by 1

Built on by

Not cited yet.