# Automated Data Visualization from Natural Language via Large Language Models: An Exploratory Study

arXiv: https://arxiv.org/abs/2404.17136 · HTML: https://mlsanity.com/paper/2404.17136/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 26 Apr 2024.

## Builds on (most cited first, 6 of 6)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)

## Built on by (most cited first, 27 of 27)

- [WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualization](https://mlsanity.com/paper/2408.01703/) (2024)
- [TikZero: Zero-Shot Text-Guided Graphics Program Synthesis](https://mlsanity.com/paper/2503.11509/) (2025)
- [nvAgent: Automated Data Visualization from Natural Language via Collaborative Agent Workflow](https://mlsanity.com/paper/2502.05036/) (2025)
- [NLI4VolVis: Natural Language Interaction for Volume Visualization via LLM Multi-Agents and Editable 3D Gaussian Splatting](https://mlsanity.com/paper/2507.12621/) (2025)
- [From Data to Story: Towards Automatic Animated Data Video Creation with LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2408.03876/) (2024)
- [The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective](https://mlsanity.com/paper/2407.08583/) (2024)
- [CoDA: Agentic Systems for Collaborative Data Visualization](https://mlsanity.com/paper/2510.03194/) (2025)
- [HyperG: Hypergraph-Enhanced LLMs for Structured Knowledge](https://mlsanity.com/paper/2502.18125/) (2025)
- [Data-to-Dashboard: Multi-Agent LLM Framework for Insightful Visualization in Enterprise Analytics](https://mlsanity.com/paper/2505.23695/) (2025)
- [Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance](https://mlsanity.com/paper/2601.14171/) (2026)
- [DataLab: A Unified Platform for LLM-Powered Business Intelligence](https://mlsanity.com/paper/2412.02205/) (2024)
- [DeepVIS: Bridging Natural Language and Data Visualization Through Step-wise Reasoning](https://mlsanity.com/paper/2508.01700/) (2025)
- [Natural Language Generation for Visualizations: State of the Art, Challenges and Future Directions](https://mlsanity.com/paper/2409.19747/) (2024)
- [Exploring Multimodal Prompt for Visualization Authoring with Large Language Models](https://mlsanity.com/paper/2504.13700/) (2025)
- [ChartCards: A Chart-Metadata Generation Framework for Multi-Task Chart Understanding](https://mlsanity.com/paper/2505.15046/) (2025)
- [QUIS: Question-guided Insights Generation for Automated Exploratory Data Analysis](https://mlsanity.com/paper/2410.10270/) (2024)
- [LoopServe: An Adaptive Dual-phase LLM Inference Acceleration System for Multi-Turn Dialogues](https://mlsanity.com/paper/2507.13681/) (2025)
- [Chatting with Logs: An exploratory study on Finetuning LLMs for LogQL](https://mlsanity.com/paper/2412.03612/) (2024)
- [Do LLMs Understand Collaborative Signals? Diagnosis and Repair](https://mlsanity.com/paper/2505.20730/) (2025)
- [MultiMat: Multimodal Program Synthesis for Procedural Materials using Large Multimodal Models](https://mlsanity.com/paper/2509.22151/) (2025)
- [Formative Study for AI-assisted Data Visualization](https://mlsanity.com/paper/2409.06892/) (2024)
- [The Role of Accuracy and Validation Effectiveness in Conversational Business Analytics](https://mlsanity.com/paper/2411.12128/) (2024)
- [VizGen: Data Exploration and Visualization from Natural Language via a Multi-Agent AI Architecture](https://mlsanity.com/paper/2509.22218/) (2025)
- [Evaluating Prompting Strategies for Chart Question Answering with Large Language Models](https://mlsanity.com/paper/2603.22288/) (2026)
- [Discovery Agents for Real-Time Analytics: Toward Proactive Insight Systems](https://mlsanity.com/paper/2605.27571/) (2026)
- [NL2Scratch: An Executable Benchmark and Evaluation for Block-Based Programming](https://mlsanity.com/paper/2606.22061/) (2026)
- [DataWeave: Deploying Human-LLM Analytics for Exploratory Structured Data Analysis](https://mlsanity.com/paper/2610.02679/) (2026)

## Abstract (arXiv)

The Natural Language to Visualization (NL2Vis) task aims to transform natural-language descriptions into visual representations for a grounded table, enabling users to gain insights from vast amounts of data. Recently, many deep learning-based approaches have been developed for NL2Vis. Despite the considerable efforts made by these approaches, challenges persist in visualizing data sourced from unseen databases or spanning multiple tables. Taking inspiration from the remarkable generation capabilities of Large Language Models (LLMs), this paper conducts an empirical study to evaluate their potential in generating visualizations, and explore the effectiveness of in-context learning prompts for enhancing this task. In particular, we first explore the ways of transforming structured tabular data into sequential text prompts, as to feed them into LLMs and analyze which table content contributes most to the NL2Vis. Our findings suggest that transforming structured tabular data into programs is effective, and it is essential to consider the table schema when formulating prompts. Furthermore, we evaluate two types of LLMs: finetuned models (e.g., T5-Small) and inference-only models (e.g., GPT-3.5), against state-of-the-art methods, using the NL2Vis benchmarks (i.e., nvBench). The experimental results reveal that LLMs outperform baselines, with inference-only models consistently exhibiting performance improvements, at times even surpassing fine-tuned models when provided with certain few-shot demonstrations through in-context learning. Finally, we analyze when the LLMs fail in NL2Vis, and propose to iteratively update the results using strategies such as chain-of-thought, role-playing, and code-interpreter. The experimental results confirm the efficacy of iterative updates and hold great potential for future study.