Conversational AI Threads for Visualizing Multidimensional Datasets
This work addresses the challenge of enhancing data visualization tools for analysts using conversational AI, though it is incremental as it builds on prior chatbot studies.
The researchers tackled the problem of using LLMs for creating and refining visualizations via conversational interfaces, finding that existing LLM-driven chatbots fell short in supporting progressive refinements, and they developed AI Threads, a multi-threaded chatbot that improved efficacy as shown in a study with 40 participants and 10 expert interviews.
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.