Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?

Abstract

Charts are ubiquitous as they help people understand and reason with data. Recently, various downstream tasks, such as chart question answering, chart captioning, etc. have emerged. Large Vision-Language Models (LVLMs) show promise in tackling these tasks, but their qualitative evaluation is costly and time-consuming, limiting real-world deployment. While using LVLMs as judges to assess chart comprehension capabilities of other LVLMs could streamline evaluation processes, challenges like proprietary datasets, restricted access to powerful models, and evaluation costs hinder their adoption in industrial settings. To this end, we present a comprehensive evaluation of 13 open-source LVLMs as judges for diverse chart comprehension and reasoning tasks. We design both pairwise and pointwise evaluation tasks covering criteria like factual correctness, informativeness, and relevancy. Additionally, we analyze LVLM judges based on format adherence, positional consistency, length bias, and instruction-following. We focus on cost-effective LVLMs (≤ 9B parameters) suitable for both research and commercial use, following a standardized evaluation protocol and rubric to measure the LVLM judge accuracy. Experimental results reveal notable variability: while some open LVLM judges achieve GPT-4level evaluation performance (about 80% agreement with GPT-4 judgments), others struggle (below 10% agreement). Our findings highlight that state-of-the-art open-source LVLMs can serve as cost-effective automatic evaluators for chart-related tasks, though biases such as positional preference and length bias persist.