Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shen, Hanwen, Ying, Ting
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.12572
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909707908677632
author Shen, Hanwen
Ying, Ting
author_facet Shen, Hanwen
Ying, Ting
contents A two stage novel generation framework (outline -> section outline -> manuscript) is widely used in long novel generation,(e.g., \textsc{DOME}, \textsc{Plan\&Write}, \textsc{Long Writer}), but study of such framework in ultra long novel(>1M words) reconstruction is little. Building on recent text compression methods (\textsc{LLMZip}, \textsc{LLM2Vec}), 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12572
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Measuring Information Distortion in Hierarchical Ultra long Novel Reconstruction:The Optimal Expansion Ratio
Shen, Hanwen
Ying, Ting
Computation and Language
Artificial Intelligence
Information Theory
A two stage novel generation framework (outline -> section outline -> manuscript) is widely used in long novel generation,(e.g., \textsc{DOME}, \textsc{Plan\&Write}, \textsc{Long Writer}), but study of such framework in ultra long novel(>1M words) reconstruction is little. Building on recent text compression methods (\textsc{LLMZip}, \textsc{LLM2Vec}), 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.
title Measuring Information Distortion in Hierarchical Ultra long Novel Reconstruction:The Optimal Expansion Ratio
topic Computation and Language
Artificial Intelligence
Information Theory
url https://arxiv.org/abs/2505.12572