arXiv cs.CL· Aolin Li, Xiao Xu, Haihua Xie·· 2 天前AI 评分22
SceneWeave：面向戏剧改编的受众引导场景探索
SceneWeave: Audience-Guided Scene Exploration for Dramatic Adaptation
AI 导读
SceneWeave 通过撰写焦点场景的对比版本、比较其产生的互动效果，再据此修改人物塑造、前置铺垫、后续发展与场景顺序，最终生成完整剧本，让实际场景写作反哺改编决策并贯穿全篇。该研究同时开发了专用写作模型与人类偏好模型，后者结合人工与合成监督信号。盲测读者对比显示 SceneWeave 优于基线流程与基于描述的对照组，内容评估表明叙事冗余减少且心理刻画更强。
正文 · 原文
Abstract:Adapting prose into a script requires transforming narration and inner experience into scenes that convey relationships and psychological contradictions. Planning specifies intended effects but leaves their realization in dialogue and action unresolved. Drawing on screenwriters' accounts of revising scenes and their connections to the surrounding work, we present SceneWeave, which uses alternative scene drafts to revise the adaptation as a whole. It writes contrasting treatments of a focal scene, compares the interactions they create, and revises characterization, preceding preparation, subsequent development, and scene order before generating the complete script. The central contribution is to use actual scene writing to inform adaptation decisions and propagate their consequences across the work. We also develop a task-specific writing model and a human-preference model for comparing script drafts. The writing model learns from adaptation examples and human preferences; the preference model combines human and synthetic supervision. Blind reader comparisons favor SceneWeave over a baseline workflow and description-based controls, while content assessment indicates reduced narrative redundancy and strong psychological treatment.
| Comments: | 13 pages, 2 figures, 3 tables |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.21737 [cs.CL] |
| (or arXiv:2610.21737v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21737 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Aolin Li [view email]
[v1]
Thu, 15 Oct 2026 11:54:45 UTC (11,632 KB)
来源：arXiv cs.CL · arxiv.org