IEEE VIS 2025 Supplemental Materials - LVLMs and Aesthetics

This repository contains supplementary materials for our study on Large Vision Language Models (LVLMs) and their effectiveness in evaluating data visualizations. The dataset includes student-created visualizations, expert annotations, model evaluations, and training data used for Retrieval-Augmented Generation (RAG).The repository is organized into the following folders:📁 Data VisualizationsContains 11 student-created data visualizations used in the study.Each visualization serves as input for LVLM evaluations.📁 Evaluation ResultsIncludes annotations for each visualization from:Expert evaluation ("ground truth").10 LVLMs (both base and RAG variants).Evaluations assess alignment with visualization principles, interpretability, and coherence.📁 Training DataContains Tufte & Wilkinson’s books used for Retrieval-Augmented Generation (RAG).These texts provide background knowledge for models incorporating retrieval-based improvements to the base models.