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

2026-01-04

arXiv.org

AI Summary

Existing end-to-end approaches to dashboard generation suffer from entangled analytical logic and visual presentation, leading to representation redundancy, poor controllability, and inefficiency. This work proposes NL2Dashboard, a novel framework that introduces a decoupled analysis-presentation architecture. It leverages a structured intermediate representation (IR) to guide large language models in focusing solely on data analysis and intent translation, while a deterministic rendering engine handles visualization synthesis. Furthermore, the framework incorporates an IR-based multi-agent tool system to enhance interactivity and precision. This design significantly improves generation efficiency and controllability, achieving superior visual quality, higher token efficiency across multiple domains, and fine-grained control in both dashboard generation and modification tasks.

Technology Category

• Natural Language Processing: Generation
• Computer Vision: Visual Reasoning & Symbolic Representations
• Data Mining & Knowledge Management: Data Visualization & Summarization

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

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 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.

Problem

• dashboard generation
• Large Language Models
• controllability
• representation redundancy
• visual synthesis

Innovation

• Analysis-Presentation Decoupling
• Intermediate Representation
• LLM-based Dashboard Generation
• Token Efficiency
• Controllable Visualization