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

arXiv: https://arxiv.org/abs/2505.12572 · HTML: https://mlsanity.com/paper/2505.12572/

## 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 (most cited first, 21 of 21)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Plan-And-Write: Towards Better Automatic Storytelling](https://mlsanity.com/paper/1811.05701/) (2018)
- [A Contrastive Framework for Neural Text Generation](https://mlsanity.com/paper/2202.06417/) (2022)
- [Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff](https://mlsanity.com/paper/1901.07821/) (2019)
- [Generative artificial intelligence enhances creativity but reduces the diversity of novel content](https://mlsanity.com/paper/2312.00506/) (2023)
- [LongLaMP: A Benchmark for Personalized Long-form Text Generation](https://mlsanity.com/paper/2407.11016/) (2024)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2105.10311/) (2021)
- [The Next Chapter: A Study of Large Language Models in Storytelling](https://mlsanity.com/paper/2301.09790/) (2023)
- [Long Text Generation by Modeling Sentence-Level and Discourse-Level Coherence](https://mlsanity.com/paper/2105.08963/) (2021)
- [GPT-who: An Information Density-based Machine-Generated Text Detector](https://mlsanity.com/paper/2310.06202/) (2023)
- [DeepZip: Lossless Data Compression using Recurrent Neural Networks](https://mlsanity.com/paper/1811.08162/) (2018)
- [Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancement](https://mlsanity.com/paper/2412.13575/) (2024)
- [Language Models can Self-Lengthen to Generate Long Texts](https://mlsanity.com/paper/2410.23933/) (2024)
- [Improving Pacing in Long-Form Story Planning](https://mlsanity.com/paper/2311.04459/) (2023)
- [Semantic Similarity Matching for Patent Documents Using Ensemble BERT-related Model and Novel Text Processing Method](https://mlsanity.com/paper/2401.06782/) (2024)
- [LongEval: A Comprehensive Analysis of Long-Text Generation Through a Plan-based Paradigm](https://mlsanity.com/paper/2502.19103/) (2025)
- [How good is my story? Towards quantitative metrics for evaluating LLM-generated XAI narratives](https://mlsanity.com/paper/2412.10220/) (2024)
- [A Comparison of Document Similarity Algorithms](https://mlsanity.com/paper/2304.01330/) (2023)

## 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.