arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.06126cs.AI
收藏

NL2Dashboard: 一种轻量且可控的基于LLM生成仪表盘的框架

NL2Dashboard: A Lightweight and Controllable Framework for Generating Dashboards with LLMs

Jiutian Research, China Mobile(九天研究,中国移动)

Boshen Shi, Kexin Yang, Yuanbo Yang, Guanguang Chang, Ce Chi, Zhendong Wang, Xing Wang, Junlan Feng

AI总结:

NL2Dashboard通过分析-呈现解耦原理,提出轻量可控的仪表盘生成框架,实现高效视觉质量和高可控性。

摘要:

尽管大型语言模型(LLMs)在生成独立图表方面表现出色,但综合生成全面的仪表盘仍是一个严峻的挑战。现有的端到端方法通常将仪表盘生成视为直接代码生成任务(例如原始HTML),存在两个根本性的局限性:由于大量令牌用于视觉渲染导致的表示冗余,以及由于分析推理与呈现交织导致的可控性低。为了解决这些挑战,我们提出了NL2Dashboard,一种基于分析-呈现解耦原理的轻量框架。我们引入了一个结构化的中间表示(IR),该表示封装了仪表盘的内容、布局和视觉元素。因此,它将LLM的角色限制在数据分析和意图翻译上,同时将视觉合成卸载到确定性渲染引擎上。基于此框架,我们开发了一个多智能体系统,其中IR驱动的算法被实例化为一组工具。全面的实验表明,该系统在不同领域中显著优于最先进的基线方法,实现了更高质量的视觉效果、显著更高的令牌效率以及在生成和修改任务中精确的可控性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑