Automated Data Visualization from Natural Language via Large Language Models: An Exploratory Study
Summary: Empirical NL2Vis study showing LLMs can outperform prior deep models on unseen/multi-table tables, especially with schema-aware prompt serialization and few-shot in-context learning. Also probes failure modes and iterative refinement (CoT/role-play/code interpreter) to improve generated visualizations. (summarized by gpt-5.4-mini on May 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Yang Wu (Huazhong University of Science and Technology)
- 2. Yao Wan (Huazhong University of Science and Technology)
- 3. Hongyu Zhang (Chongqing University)
- 4. Yulei Sui (University of New South Wales)
- 5. Wucai Wei (Huazhong University of Science and Technology)
- 6. Wei Zhao (Huazhong University of Science and Technology)
- 7. Guandong Xu (University of Technology Sydney)
- 8. Hai Jin (Huazhong University of Science and Technology)
BibTeX Citation
@inproceedings{wu_sigmod24,
title = {{Automated Data Visualization from Natural Language via Large Language Models: An Exploratory Study}},
author = {Wu, Yang and Wan, Yao and Zhang, Hongyu and Sui, Yulei and Wei, Wucai and Zhao, Wei and Xu, Guandong and Jin, Hai},
series = {{SIGMOD} '24},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3654992},
url = {https://dl.acm.org/doi/10.1145/3654992},
year = {2024}
}
Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 7,809 | Can Large Language Models Be Query Optimizer for Relational Databases? | 2026 | SIGMOD | 5.5399022e-05 |
| 10,444 | DIVER: A Robust Text-to-SQL System with Dynamic Interactive Value Linking and Evidence Reasoning | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 3 of 3 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 865 | Natural language to SQL: Where are we today? | 2020 | VLDB | 0.00013521464 |
| 4,809 | Synthesizing Natural Language to Visualization (NL2VIS) Benchmarks from NL2SQL Benchmarks | 2021 | SIGMOD | 6.4984309e-05 |
| 5,634 | DeepEye: Creating Good Data Visualizations by Keyword Search | 2018 | SIGMOD | 6.1412942e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 279 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB |
| 2 | 9,293 | Intelligent Agents for Data Exploration | 2024 | VLDB |
| 3 | 6,101 | LLM for Data Management | 2024 | VLDB |
| 4 | 10,510 | NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions | 2026 | VLDB |
| 5 | 10,474 | MultiVis-Agent: A Multi-Agent Framework with Logic Rules for Reliable and Comprehensive Cross-Modal Data Visualization | 2026 | SIGMOD |
| 6 | 11,013 | Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models | 2025 | VLDB |
| 7 | 2,602 | NL2SQL is a solved problem... Not! | 2024 | CIDR |
| 8 | 9,870 | Natural Language to SQL: State of the Art and Open Problems | 2025 | VLDB |
| 9 | 3,787 | Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL | 2024 | VLDB |
| 10 | 4,809 | Synthesizing Natural Language to Visualization (NL2VIS) Benchmarks from NL2SQL Benchmarks | 2021 | SIGMOD |