Conversational AI Threads for Visualizing Multidimensional Datasets

TL;DR

This paper investigates the use of Large Language Models for creating interactive visualizations of multidimensional datasets, highlighting their potential and limitations, and introduces AI Threads to enhance analytic conversations.

Contribution

It introduces AI Threads, a multi-threaded chatbot system that improves conversational context management for data visualization tasks.

Findings

LLMs can assist in visual data analysis but struggle with progressive refinement.

AI Threads enhances conversational control and visualization quality.

Study shows promising potential of LLMs with identified challenges.

Abstract

Generative Large Language Models (LLMs) show potential in data analysis, yet their full capabilities remain uncharted. Our work explores the capabilities of LLMs for creating and refining visualizations via conversational interfaces. We used an LLM to conduct a re-analysis of a prior Wizard-of-Oz study examining the use of chatbots for conducting visual analysis. We surfaced the strengths and weaknesses of LLM-driven analytic chatbots, finding that they fell short in supporting progressive visualization refinements. From these findings, we developed AI Threads, a multi-threaded analytic chatbot that enables analysts to proactively manage conversational context and improve the efficacy of its outputs. We evaluate its usability through a crowdsourced study (n=40) and in-depth interviews with expert analysts (n=10). We further demonstrate the capabilities of AI Threads on a dataset outside the LLM's training corpus. Our findings show the potential of LLMs while also surfacing challenges and fruitful avenues for future research.