StorySpark：面向故事前提生成的模块级进化搜索

中文摘要 AI 辅助

故事前提是催生完整叙事的创意火花，然而基于大语言模型（LLM）的故事生成大多侧重后期规划、可控性、连贯性和散文扩展，前提层面的创意构思却相对未得到充分探索。本文提出StorySpark，一种面向故事前提生成的模块级进化搜索框架。StorySpark在可解释的叙事模块（如背景、人物设定、事件、结局和转折）上运行，将每个活跃模块视为并非仅需填充一次的静态领域，而是由当前已构建的部分前提所决定的局部搜索空间。对于每个模块，它会生成备选方案、在上下文中评估它们、通过反馈驱动的变异与重组对其进行优化、借助帕累托引导的选择保留互补优势，并重新分配前沿容量以平衡分支覆盖与有前景的方向。多视角自动评估与人工评估显示，StorySpark生成的最终前提优于竞争性基线，尤其在创意性上表现出持续提升；当由同一位故事创作者进行扩展时，其前提还能生成更高质量的下游故事，同时保持完整性、吸引力和多样化的可用叙事方向。

英文摘要

A story premise is the creative spark from which a full narrative can grow. Yet LLM-based story generation has mostly emphasized later-stage planning, controllability, coherence, and prose expansion, while premise-level ideation remains comparatively underexplored. We introduce StorySpark, a module-wise evolutionary search framework for story premise generation. StorySpark operates over interpretable narrative modules such as background, persona, event, ending, and twist, treating each active module not as a static field to fill once, but as a local search space conditioned on the partial premise built so far. For each module, it generates alternatives, evaluates them in context, refines them through feedback-driven mutation and recombination, preserves complementary strengths with Pareto-guided selection, and reallocates frontier capacity to balance branch coverage with promising directions. Multi-view automatic and human evaluations show that StorySpark produces stronger final premises than competitive baselines, with especially consistent gains in originality; when expanded with the same story writer, its premises also lead to higher-quality downstream stories while maintaining completeness, fascination, and diverse usable narrative directions.

发表机构

• The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
• Renmin University of China（中国人民大学）
• Shandong University（山东大学）
• Institute of Deep Perception Technology, JITRI（JITRI深度感知技术研究院）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

26 pages, 7 figures