Controllable Narrative Rendering for Enhanced Assisted Writing
Controllable Narrative Rendering for Enhanced Assisted Writing
用于增强辅助写作的可控叙事渲染
Abstract: Despite the remarkable proficiency of large language models (LLMs) in basic writing assistance, their utility in creative writing is fundamentally hindered by a persistent binary failure. This issue manifests as an oscillation between safe, surface-level editing, referred to as remedial polishing, and destructive, uncontrolled plot expansion. This dilemma defines a critical trade-off between narrative fidelity and descriptive intensity.
摘要： 尽管大型语言模型（LLMs）在基础写作辅助方面表现出色，但它们在创意写作中的应用却受到一种持续存在的二元失效问题的根本阻碍。这一问题表现为在“补救性润色”（即安全但浅层的编辑）与“破坏性且失控的情节扩展”之间反复摇摆。这种困境定义了叙事保真度与描述强度之间关键的权衡关系。
We propose Loom, an assisted writing framework grounded in the narratological distinction between story and discourse. Loom employs a three-layer pipeline that operationalizes an intent-centered semiotic chain-of-thought to enforce precise control over narrative intent and rendering density. This architecture separates the generation of perceptual material from syntactic insertion, ensuring that enhancement occurs without violating the original event structure.
我们提出了 Loom，这是一个基于叙事学中“故事”（story）与“话语”（discourse）区别的辅助写作框架。Loom 采用了一个三层流水线，通过操作以意图为中心的符号化思维链（semiotic chain-of-thought），对叙事意图和渲染密度进行精确控制。该架构将感知素材的生成与句法插入分离开来，确保在不破坏原始事件结构的前提下实现内容增强。
Our comprehensive evaluation, which includes LLM-based metrics and human assessment, demonstrates that Loom successfully resolves this fundamental tension. Loom achieves the highest overall quality score, yielding substantial gains in factual integrity and descriptive intensity compared to state-of-the-art baselines.
我们的综合评估（包括基于 LLM 的指标和人工评估）表明，Loom 成功解决了这一根本性矛盾。与当前最先进的基准模型相比，Loom 获得了最高的整体质量评分，并在事实完整性和描述强度方面取得了显著提升。
Paper Details:
- Authors: Mingzhe Lu, Yanbing Liu, Jiayue Wu, Jiarui Zhang, Qihao Wang, Yue Hu, Yunpeng Li, Yangyan Xu
- arXiv ID: 2607.00009
- Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
论文详情：
- 作者： Mingzhe Lu, Yanbing Liu, Jiayue Wu, Jiarui Zhang, Qihao Wang, Yue Hu, Yunpeng Li, Yangyan Xu
- arXiv ID: 2607.00009
- 学科分类： 计算与语言 (cs.CL)；人工智能 (cs.AI)