用分步设计让大模型更高效生成可控的可视化仪表板。
NL2Dashboard: A Lightweight and Controllable Framework for Generating Dashboards with LLMs
- 将分析与展示分离，用结构化中间表示降低生成负担。
- 相比现有方法，视觉质量更高，节省超过60%的生成token。
- 适合需要快速迭代和精准控制的商业数据可视化场景。
尽管大型语言模型在生成独立图表方面表现出色，但生成综合性仪表板仍面临重大挑战。现有端到端范式通常将仪表板生成视为直接代码生成任务（如原始HTML），存在两个根本性局限：视觉渲染消耗大量令牌导致表示冗余，以及分析推理与展示耦合导致可控性差。为此，我们提出NL2Dashboard，一个基于分析-展示解耦原则的轻量级框架。引入一种结构化的中间表示（IR），封装仪表板的内容、布局和视觉元素，从而将LLM的角色限定在数据分析与意图转换，而将视觉合成交由确定性渲染引擎处理。基于此框架，我们构建了一个多智能体系统，其中以IR驱动的算法被实现为一组工具。全面实验表明，NL2Dashboard在多个领域显著优于现有最佳基线，在视觉质量、令牌效率和生成与修改任务中的精确可控性方面均表现优异。
原文摘要 · Abstract (English)
While Large Language Models (LLMs) have demonstrated remarkable proficiency in generating standalone charts, synthesizing comprehensive dashboards remains a formidable challenge. Existing end-to-end paradigms, which typically treat dashboard generation as a direct code generation task (e.g., raw HTML), suffer from two fundamental limitations: representation redundancy due to massive tokens spent on visual rendering, and low controllability caused by the entanglement of analytical reasoning and presentation. To address these challenges, we propose NL2Dashboard, a lightweight framework grounded in the principle of Analysis-Presentation Decoupling. We introduce a structured intermediate representation (IR) that encapsulates the dashboard's content, layout, and visual elements. Therefore, it confines the LLM's role to data analysis and intent translation, while offloading visual synthesis to a deterministic rendering engine. Building upon this framework, we develop a multi-agent system in which the IR-driven algorithm is instantiated as a suite of tools. Comprehensive experiments conducted with this system demonstrate that NL2Dashboard significantly outperforms state-of-the-art baselines across diverse domains, achieving superior visual quality, significantly higher token efficiency, and precise controllability in both generation and modification tasks.
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。