NL2Dashboard: A Lightweight and Controllable Framework for Generating Dashboards with LLMs
Boshen Shi, Kexin Yang, Yuanbo Yang, Guanguang Chang, Ce Chi, Zhendong Wang, Xing Wang, Junlan Feng

TL;DR
NL2Dashboard introduces a decoupled framework for dashboard generation using LLMs, improving control, efficiency, and visual quality by separating analysis from presentation and employing a structured intermediate representation.
Contribution
It proposes a novel decoupling approach with a structured IR and multi-agent system, enhancing controllability and efficiency in LLM-based dashboard generation.
Findings
Outperforms state-of-the-art baselines in visual quality
Achieves higher token efficiency
Provides precise controllability in generation and modification
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsData Visualization and Analytics · Multimodal Machine Learning Applications · Handwritten Text Recognition Techniques
