# Chat2VIS: Generating Data Visualisations via Natural Language using ChatGPT, Codex and GPT-3 Large Language Models

arXiv: https://arxiv.org/abs/2302.02094 · HTML: https://mlsanity.com/paper/2302.02094/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Feb 2023.

## Built on by (most cited first, 30 of 59)

- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models](https://mlsanity.com/paper/2304.01852/) (2023)
- [Large Language Models and Games: A Survey and Roadmap](https://mlsanity.com/paper/2402.18659/) (2024)
- [Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions](https://mlsanity.com/paper/2305.10435/) (2023)
- [VisEval: A Benchmark for Data Visualization in the Era of Large Language Models](https://mlsanity.com/paper/2407.00981/) (2024)
- [Advancements in Generative AI: A Comprehensive Review of GANs, GPT, Autoencoders, Diffusion Model, and Transformers](https://mlsanity.com/paper/2311.10242/) (2023)
- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)
- [Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey](https://mlsanity.com/paper/2310.17894/) (2023)
- [Benchmarking Visual Language Models on Standardized Visualization Literacy Tests](https://mlsanity.com/paper/2503.16632/) (2025)
- [Decoding ChatGPT: A Taxonomy of Existing Research, Current Challenges, and Possible Future Directions](https://mlsanity.com/paper/2307.14107/) (2023)
- [From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape](https://mlsanity.com/paper/2312.10868/) (2023)
- [LLM/Agent-as-Data-Analyst: A Survey](https://mlsanity.com/paper/2509.23988/) (2025)
- [Towards Generating Functionally Correct Code Edits from Natural Language Issue Descriptions](https://mlsanity.com/paper/2304.03816/) (2023)
- [Unlocking the Potential of ChatGPT: A Comprehensive Exploration of its Applications, Advantages, Limitations, and Future Directions in Natural Language Processing](https://mlsanity.com/paper/2304.02017/) (2023)
- [Probing the Visualization Literacy of Vision Language Models: the Good, the Bad, and the Ugly](https://mlsanity.com/paper/2504.05445/) (2025)
- [Vi(E)va LLM! A Conceptual Stack for Evaluating and Interpreting Generative AI-based Visualizations](https://mlsanity.com/paper/2402.02167/) (2024)
- [VIS-Shepherd: Constructing Critic for LLM-based Data Visualization Generation](https://mlsanity.com/paper/2506.13326/) (2025)
- [MyCrunchGPT: A chatGPT assisted framework for scientific machine learning](https://mlsanity.com/paper/2306.15551/) (2023)
- [DataLab: A Unified Platform for LLM-Powered Business Intelligence](https://mlsanity.com/paper/2412.02205/) (2024)
- [VizGenie: Toward Self-Refining, Domain-Aware Workflows for Next-Generation Scientific Visualization](https://mlsanity.com/paper/2507.21124/) (2025)
- [DeepVIS: Bridging Natural Language and Data Visualization Through Step-wise Reasoning](https://mlsanity.com/paper/2508.01700/) (2025)
- [Testing the Depth of ChatGPT's Comprehension via Cross-Modal Tasks Based on ASCII-Art: GPT3.5's Abilities in Regard to Recognizing and Generating ASCII-Art Are Not Totally Lacking](https://mlsanity.com/paper/2307.16806/) (2023)
- [Exploring the Limits of ChatGPT in Software Security Applications](https://mlsanity.com/paper/2312.05275/) (2023)
- [The Impact of Artificial Intelligence on the Evolution of Digital Education: A Comparative Study of OpenAI Text Generation Tools including ChatGPT, Bing Chat, Bard, and Ernie](https://mlsanity.com/paper/2309.02029/) (2023)
- [Large Language Models for the Automated Analysis of Optimization Algorithms](https://mlsanity.com/paper/2402.08472/) (2024)
- [AuraGenome: An LLM-Powered Framework for On-the-Fly Reusable and Scalable Circular Genome Visualizations](https://mlsanity.com/paper/2507.02877/) (2025)
- [Evaluating LLMs for Visualization Generation and Understanding](https://mlsanity.com/paper/2507.22890/) (2025)
- [Had enough of experts? Quantitative knowledge retrieval from large language models](https://mlsanity.com/paper/2402.07770/) (2024)
- [V-RECS, a Low-Cost LLM4VIS Recommender with Explanations, Captioning and Suggestions](https://mlsanity.com/paper/2406.15259/) (2024)
- [Multi-Agent Actor-Critic Generative AI for Query Resolution and Analysis](https://mlsanity.com/paper/2502.13164/) (2025)

## Abstract (arXiv)

The field of data visualisation has long aimed to devise solutions for generating visualisations directly from natural language text. Research in Natural Language Interfaces (NLIs) has contributed towards the development of such techniques. However, the implementation of workable NLIs has always been challenging due to the inherent ambiguity of natural language, as well as in consequence of unclear and poorly written user queries which pose problems for existing language models in discerning user intent. Instead of pursuing the usual path of developing new iterations of language models, this study uniquely proposes leveraging the advancements in pre-trained large language models (LLMs) such as ChatGPT and GPT-3 to convert free-form natural language directly into code for appropriate visualisations. This paper presents a novel system, Chat2VIS, which takes advantage of the capabilities of LLMs and demonstrates how, with effective prompt engineering, the complex problem of language understanding can be solved more efficiently, resulting in simpler and more accurate end-to-end solutions than prior approaches. Chat2VIS shows that LLMs together with the proposed prompts offer a reliable approach to rendering visualisations from natural language queries, even when queries are highly misspecified and underspecified. This solution also presents a significant reduction in costs for the development of NLI systems, while attaining greater visualisation inference abilities compared to traditional NLP approaches that use hand-crafted grammar rules and tailored models. This study also presents how LLM prompts can be constructed in a way that preserves data security and privacy while being generalisable to different datasets. This work compares the performance of GPT-3, Codex and ChatGPT across a number of case studies and contrasts the performances with prior studies.