Pastiche Novel Generation Creating: Fan Fiction You Love in Your Favorite Author's Style
Xueran Han, Yuhan Liu, Mingzhe Li, Wei Liu, Sen Hu, Rui Yan, Zhiqiang, Xu, Xiuying Chen

TL;DR
This paper introduces Pastiche Novel Generation, a system that imitates an author's style and character to generate coherent, faithful narratives, advancing literary AI with a curriculum learning approach.
Contribution
It proposes WriterAgent, a novel hierarchical generation system trained via curriculum learning to master stylistic, character, and plot aspects for pastiche novel creation.
Findings
Outperforms baselines in style and character fidelity
Successfully generates coherent narratives in multiple languages
Demonstrates effectiveness on classics like Harry Potter and Dream of the Red Chamber
Abstract
Great novels create immersive worlds with rich character arcs, well-structured plots, and nuanced writing styles. However, current novel generation methods often rely on brief, simplistic story outlines and generate details using plain, generic language. To bridge this gap, we introduce the task of Pastiche Novel Generation, which requires the generated novels to imitate the distinctive features of the original work, including understanding character profiles, predicting plausible plot developments, and writing concrete details using vivid, expressive language. To achieve this, we propose WriterAgent, a novel generation system designed to master the core aspects of literary pastiche. WriterAgent is trained through a curriculum learning paradigm, progressing from low-level stylistic mastery to high-level narrative coherence. Its key tasks include language style learning, character…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
