Generating Analytic Specifications for Data Visualization from Natural Language Queries using Large Language Models
Preprint
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.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural LanguageIEEE Transactions on Visualization and Computer Graphics, 2024
- Chat2VIS: Generating Data Visualizations via Natural Language Using ChatGPT, Codex and GPT-3 Large Language ModelsIEEE Access, 2023
- Natural Language to Visualization by Neural Machine TranslationIEEE Transactions on Visualization and Computer Graphics, 2021
- VITALITY: Promoting Serendipitous Discovery of Academic Literature with Transformers & Visual AnalyticsIEEE Transactions on Visualization and Computer Graphics, 2021
- NL4DV: A Toolkit for Generating Analytic Specifications for Data Visualization from Natural Language QueriesIEEE Transactions on Visualization and Computer Graphics, 2020
- Interweaving Multimodal Interaction With Flexible Unit Visualizations for Data ExplorationIEEE Transactions on Visualization and Computer Graphics, 2020
- FlowSense: A Natural Language Interface for Visual Data Exploration within a Dataflow SystemIEEE Transactions on Visualization and Computer Graphics, 2019
- Orko: Facilitating Multimodal Interaction for Visual Exploration and Analysis of NetworksIEEE Transactions on Visualization and Computer Graphics, 2017
- Choosing an Effective Visual2015
- A Multi-Modal Natural Language Interface to an Information Visualization EnvironmentInternational Journal of Speech Technology, 2001