让故事更贴合读者偏好，关键在理解上下文而非只改风格。
StoryLens: Preference-Aligned Story Rewriting via Context-Aware Narrative Enrichment
- 基于上下文增强重写，避免仅表面改风格。
- 读者满意度提升24.5%，远超单纯风格调整的2.3%。
- 适合做个性化内容生成、智能写作系统的研究者。
故事重写旨在根据读者偏好调整现有叙事，同时保持情节一致性和连贯性。与传统风格迁移不同，我们认为有效重写需超越表层风格变换，实现上下文感知的叙事丰富。初步人类研究表明，仅风格适配带来微弱满意度提升（2.3%），而上下文增强重写显著改善用户偏好契合度（24.5%）。为此，我们构建了STORYLENSBENCH，一个大规模偏好对齐故事重写基准，包含结构化故事书、多维读者偏好画像及上下文感知重写故事排名。基于此，提出STORYLENSEVAL奖励模型以评估重写故事的用户满意度，以及STORYLENSWRITER两阶段重写模型，结合监督微调与基于GRPO的强化学习。建立涵盖保真度、连贯性和用户满意度的综合评估框架。实验表明，STORYLENSWRITER持续优于强基线生成与个性化模型，凸显上下文感知叙事丰富对个性化故事重写的决定性作用。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。