StoryLens: Preference-Aligned Story Rewriting via Context-Aware Narrative Enrichment

2026-05-27

AI Summary

This work addresses the challenge that existing story rewriting methods struggle to simultaneously preserve narrative consistency and align with reader preferences. To this end, we propose StoryLensWriter, a two-stage context-aware rewriting model that integrates supervised fine-tuning with GRPO-based reinforcement learning. We also introduce StoryLensBench—the first structured benchmark for preference-aligned story rewriting—and its accompanying reward model, StoryLensEval. Our study is the first to empirically demonstrate the critical role of context-aware narrative enhancement in improving reader satisfaction, leveraging a multidimensional reader profiling framework and a hybrid evaluation protocol. Experimental results show that StoryLensWriter significantly outperforms current baselines in faithfulness, coherence, and reader satisfaction, achieving a 24.5% improvement in user preference alignment.

Abstract

Story rewriting aims to adapt existing narratives to diverse reader preferences while preserving plot consistency and narrative coherence. Unlike conventional work on style transfer, we argue that effective story rewriting demands context-aware narrative enrichment beyond surface-level stylistic adaptation. Our pilot human study shows that style adaptation alone provides only marginal gains in reader satisfaction (2.3%), while context-enhanced rewriting substantially improves user preference alignment (24.5%). Motivated by this, we introduce STORYLENSBENCH, a large-scale benchmark for preference-aligned story rewriting, comprising structured story books, multi-dimensional reader preference profiles, and ranked context-aware rewritten stories. Building on this benchmark, we propose STORYLENSEVAL, a reward model for estimating reader satisfaction over rewritten stories, and STORYLENSWRITER, a two-stage rewriting model combining supervised fine-tuning with GRPO-based reinforcement learning. We further establish a comprehensive evaluation framework covering fidelity, coherence, and reader satisfaction. Experimental results demonstrate that STORYLENSWRITER consistently outperforms strong generation and personalization baselines, highlighting the importance of context-aware narrative enrichment for personalized story rewriting.

Problem

• story rewriting
• reader preferences
• narrative coherence
• context-aware enrichment
• preference alignment

Innovation

• context-aware narrative enrichment
• preference-aligned story rewriting
• reinforcement learning
• reader satisfaction modeling
• story personalization