Rethinking NL2VIS: A comparative survey of LLM-based natural-language-to-visualisation frameworks
Publication Type
Conference Proceeding Article
Publication Date
6-2026
Abstract
Large Language Models (LLMs) are increasingly used to generate charts directly from natural-language instructions, yet their performance remains inconsistent across chart types and visualisation complexities. This paper examines a set of framework models that report results on comparable chart-generation benchmarks, enabling a clearer view of how these systems perform relative to one another. Through this comparative analysis, we identify persistent weaknesses in current LLM-based charting—such as unreliable library behaviours, loose alignment between code and visual output, and brittle reasoning that frequently fails in the absence of corrective mechanisms. We also highlight the broad strategies adopted across frameworks to address these shortcomings. Taken together, our findings suggest that future progress in Natural-Language-to-Visualisation (NL2VIS) will depend less on scaling models or increasing architectural complexity and more on developing lean, well-orchestrated systems with a stronger intrinsic understanding of how language, data, and visual semantics interact.
Keywords
Framework Models, LLM, NL2VIS, Visualisation
Discipline
Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces
Research Areas
Intelligent Systems and Optimization
Publication
Proceedings of the 30th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2026, Hong Kong, China, June 9-12
First Page
138
Last Page
155
Identifier
10.1007/978-981-92-2014-4_12
Publisher
Springer
City or Country
Cham
Citation
HOCK, Tai Lin; MA, Yunshan; and WANG, Zhaoxia.
Rethinking NL2VIS: A comparative survey of LLM-based natural-language-to-visualisation frameworks. (2026). Proceedings of the 30th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2026, Hong Kong, China, June 9-12. 138-155.
Available at: https://ink.library.smu.edu.sg/sis_research/11281
Additional URL
https://doi.org/10.1007/978-981-92-2014-4_12