让AI理解空间布局的语义互动，逐步优化叙事生成。
Semantic Prompting: Agentic Incremental Narrative Refinement through Spatial Semantic Interaction
- 通过感知语义交互，动态调整文本位置以匹配用户意图。
- 用户研究显示，14人使用后能更高效地逐步完善分析结果。
- 适合需要持续迭代、人机协作的复杂信息梳理场景。
交互式空间布局使用户能够整合信息并组织发现以支持意义建构。尽管大型语言模型（LLMs）可从空间布局自动生成叙述，但现有的基于拼贴和重生成的方法难以支持意义建构过程中固有的增量式空间优化。我们识别出三个关键缺口：交互-修订不一致、人-LLM意图错位、缺乏细粒度定制。为此，我们提出语义提示（Semantic Prompting）框架，该框架能感知语义交互、推理优化意图，并执行精准的位置修正。我们实现了S-PRISM系统来实现该框架。实证评估表明，S-PRISM有效提升了交互-修订精炼的准确性。用户研究（N=14）显示，参与者借助S-PRISM通过交互引导实现逐步形式化。结果表明，用户高度认可其高效、灵活且可信的支持，显著增强了人-LLM意图对齐。
原文摘要 · Abstract (English)
Interactive spatial layouts empower users to synthesize information and organize findings for sensemaking. While Large Language Models (LLMs) can automate narrative generation from spatial layouts, current collage-based and re-generation methods struggle to support the incremental spatial refinements inherent to the sensemaking process. We identify three critical gaps in existing spatial-textual generation: interaction-revision misalignment, human-LLM intent misalignment, and lack of granular customization. To address these, we introduce Semantic Prompting, a framework for spatial refinement that perceives semantic interactions, reasons about refinement intent, and performs targeted positional revisions. We implemented S-PRISM to realize this framework. The empirical evaluation demonstrated that S-PRISM effectively enhanced the precision of interaction-revision refinement. A user study ($N=14$) highlighted how participants leveraged S-PRISM for incremental formalization through interactive steering. Results showed that users valued its efficient, adaptable, and trustworthy support, which effectively strengthens human-LLM intent alignment.
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。