@inproceedings{wang2023llm,
author = {Wang, Lei and Zhang, Songheng and Wang, Yun and Lim, Ee-Peng and Wang, Yong},
title = {LLM4Vis: Explainable Visualization Recommendation using ChatGPT},
year = {2023},
month = {October},
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 template-based 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.},
url = {http://approjects.co.za/?big=en-us/research/publication/llm4vis-explainable-visualization-recommendation-using-chatgpt/},
}