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

arXiv: https://arxiv.org/abs/2601.06126 · HTML: https://mlsanity.com/paper/2601.06126/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 33 references that are in the map.
- First posted on arXiv 4 Jan 2026.

## Builds on (most cited first, 13 of 13)

- [PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides](https://mlsanity.com/paper/2501.03936/) (2025)
- [ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Language](https://mlsanity.com/paper/2311.01920/) (2023)
- [Towards Natural Language Interfaces for Data Visualization: A Survey](https://mlsanity.com/paper/2109.03506/) (2021)
- [Data2Vis: Automatic Generation of Data Visualizations Using Sequence to Sequence Recurrent Neural Networks](https://mlsanity.com/paper/1804.03126/) (2018)
- [METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling](https://mlsanity.com/paper/2502.17651/) (2025)
- [AI4VIS: Survey on Artificial Intelligence Approaches for Data Visualization](https://mlsanity.com/paper/2102.01330/) (2021)
- [nvAgent: Automated Data Visualization from Natural Language via Collaborative Agent Workflow](https://mlsanity.com/paper/2502.05036/) (2025)
- [Data Formulator 2: Iterative Creation of Data Visualizations, with AI Transforming Data Along the Way](https://mlsanity.com/paper/2408.16119/) (2024)
- [CoDA: Agentic Systems for Collaborative Data Visualization](https://mlsanity.com/paper/2510.03194/) (2025)
- [Prompt4Vis: Prompting Large Language Models with Example Mining and Schema Filtering for Tabular Data Visualization](https://mlsanity.com/paper/2402.07909/) (2024)
- [Data-to-Dashboard: Multi-Agent LLM Framework for Insightful Visualization in Enterprise Analytics](https://mlsanity.com/paper/2505.23695/) (2025)
- [Drillboards: Adaptive Visualization Dashboards for Dynamic Personalization of Visualization Experiences](https://mlsanity.com/paper/2410.12744/) (2024)
- [DashChat: Interactive Authoring of Performance Dashboard Design Prototypes through Conversation with LLM-Powered Agent](https://mlsanity.com/paper/2504.12865/) (2025)

## Built on by (most cited first, 1 of 1)

- [DashArena: Benchmarking LLMs on Interactive Analytic Dashboard Generation](https://mlsanity.com/paper/2608.10567/) (2026)

## Abstract (arXiv)

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.