Unraveling the Truth: Do VLMs really Understand Charts? A Deep Dive into Consistency and Robustness

TL;DR

This paper critically evaluates the robustness and consistency of state-of-the-art Visual Language Models in Chart Question Answering, revealing significant performance variations and highlighting areas for future improvement.

Contribution

It provides a comprehensive assessment of VLMs on diverse chart datasets, identifying key weaknesses and proposing directions for enhancing model robustness in CQA.

Findings

Significant performance variation across question and chart types

Current models struggle with chart and question complexity

Identified areas for improving model robustness and reliability

Abstract

Chart question answering (CQA) is a crucial area of Visual Language Understanding. However, the robustness and consistency of current Visual Language Models (VLMs) in this field remain under-explored. This paper evaluates state-of-the-art VLMs on comprehensive datasets, developed specifically for this study, encompassing diverse question categories and chart formats. We investigate two key aspects: 1) the models' ability to handle varying levels of chart and question complexity, and 2) their robustness across different visual representations of the same underlying data. Our analysis reveals significant performance variations based on question and chart types, highlighting both strengths and weaknesses of current models. Additionally, we identify areas for improvement and propose future research directions to build more robust and reliable CQA systems. This study sheds light on the limitations of current models and paves the way for future advancements in the field.