Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
12-2023
Abstract
Data visualization is a powerful tool for exploring and communicating insights in various domains. To automate visualization choice for datasets, a task known as visualization recommendation has been proposed. Various machine-learning-based approaches have been developed for this purpose, but they often require a large corpus of dataset-visualization pairs for training and lack natural explanations for their results. To address this research gap, we propose LLM4Vis, a novel ChatGPT-based prompting approach to perform visualization recommendation and return human-like explanations using very few demonstration examples. Our approach involves feature description, demonstration example selection, explanation generation, demonstration example construction, and inference steps. To obtain demonstration examples with high-quality explanations, we propose a new explanation generation bootstrapping to iteratively refine generated explanations by considering the previous generation and templatebased hint. Evaluations on the VizML dataset show that LLM4Vis outperforms or performs similarly to supervised learning models like Random Forest, Decision Tree, and MLP in both few-shot and zero-shot settings. The qualitative evaluation also shows the effectiveness of explanations generated by LLM4Vis. We make our code publicly available at https://github.com/demoleiwang/LLM4Vis.
Keywords
Dataset visualization, Example selection, Feature description, High quality, Human like, Large corpora, Learning-based approach, Machine-learning
Discipline
Artificial Intelligence and Robotics | Databases and Information Systems
Research Areas
Data Science and Engineering
Publication
2023 Conference on Empirical Methods in Natural Language Processing: Singapore, December 6-10: Proceedings
First Page
675
Last Page
692
ISBN
9798891760608
Identifier
10.18653/v1/2023.emnlp-industry.64
Publisher
Association for Computational Linguistics
City or Country
Stroudsburg, PA
Citation
WANG, Lei; ZHANG, Songheng; WANG, Yun; LIM, Ee-peng; and WANG, Yong.
LLM4Vis: Explainable visualization recommendation using ChatGPT. (2023). 2023 Conference on Empirical Methods in Natural Language Processing: Singapore, December 6-10: Proceedings. 675-692.
Available at: https://ink.library.smu.edu.sg/sis_research/8330
Copyright Owner and License
Publisher
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.18653/v1/2023.emnlp-industry.64