Title: Large Language Models as Computational Engines and Virtual Domain Experts for Visual Data Analysis

Date: Thursday, April 2, 2026
Time: 3-5pm Eastern time (U.S.)
Location: Technology Square Research Building (TSRB) 334
Virtual meeting (hybrid): https://gatech.zoom.us/j/5618662383?pwd=dTB2YjB5WnRiaHhFaHZITVNQeFJVUT09

Alexander Bendeck
Ph.D. Candidate in Computer Science 
School of Interactive Computing 
Georgia Institute of Technology

Committee
Dr. John Stasko (Advisor) - School of Interactive Computing, Georgia Institute of Technology
Dr. Alex Endert - School of Interactive Computing, Georgia Institute of Technology
Dr. Clio Andris - School of City and Regional Planning, Georgia Institute of Technology
Dr. Cindy Xiong Bearfield - School of Interactive Computing, Georgia Institute of Technology
Dr. Ross Maciejewski - School of Computing and Augmented Intelligence, Arizona State University

Abstract
Advances in generative artificial intelligence have led to the development of pre-trained large language models (LLMs) which are widely available and broadly useful. For data visualization researchers, LLMs' vast domain knowledge and computational power have the promise to extend existing research threads in exciting directions. However, well-documented hallucination and inconsistency issues with LLMs can inhibit visualization system performance and erode user trust. We also have limited formal understanding of LLMs’ ability to help analysts with specific tasks.

In my thesis work, I study the potential use of LLMs as “virtual domain experts” during visual data analysis. This includes two main goals: First, to evaluate LLMs at applying their knowledge bases to data- and chart-centric tasks; and second, to study user satisfaction and trust for LLM-powered visualization systems. I address the first goal through an empirical evaluation of the GPT-4V multimodal language model on a suite of visualization literacy tasks, demonstrating LLM performance at reading and understanding visualizations. In subsequent work, I address both goals by assessing LLMs’ domain knowledge and generative capabilities on two specific tasks: question answering and data integration. For each task, I present formative studies, empirical evaluations, and design probes using proof-of-concept visualization systems, exploring both technical and human-centered perspectives on the use of LLMs during visual data analysis.