Generating Analytic Specifications for Data Visualization from Natural Language Queries using Large Language Models

TL;DR

This paper introduces a prompt-based method using large language models to generate explainable analytic specifications from natural language queries for data visualization, enhancing interpretability and debugging.

Contribution

It presents a novel prompt design that enables LLMs to produce detailed, explainable visualization specifications and supports conversational interaction and ambiguity detection.

Findings

Preliminary evaluation with GPT-4 shows promising results.

The approach improves explainability and debuggability of NL-to-visualization translation.

Open-source implementation integrated into NL4DV toolkit.

Abstract

Recently, large language models (LLMs) have shown great promise in translating natural language (NL) queries into visualizations, but their "black-box" nature often limits explainability and debuggability. In response, we present a comprehensive text prompt that, given a tabular dataset and an NL query about the dataset, generates an analytic specification including (detected) data attributes, (inferred) analytic tasks, and (recommended) visualizations. This specification captures key aspects of the query translation process, affording both explainability and debuggability. For instance, it provides mappings from the detected entities to the corresponding phrases in the input query, as well as the specific visual design principles that determined the visualization recommendations. Moreover, unlike prior LLM-based approaches, our prompt supports conversational interaction and ambiguity detection capabilities. In this paper, we detail the iterative process of curating our prompt, present a preliminary performance evaluation using GPT-4, and discuss the strengths and limitations of LLMs at various stages of query translation. The prompt is open-source and integrated into NL4DV, a popular Python-based natural language toolkit for visualization, which can be accessed at https://nl4dv.github.io.