ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild

TL;DR

ChartGemma is a new model that improves chart understanding by training directly on chart images, capturing visual trends and patterns, and achieving state-of-the-art results across multiple benchmarks.

Contribution

It introduces a novel training approach for chart reasoning models that uses instruction-tuning data generated from chart images, enhancing performance and generalizability.

Findings

Achieves state-of-the-art results on 5 chart reasoning benchmarks.

Generates more realistic and factually accurate chart summaries.

Outperforms existing models by directly leveraging visual information.

Abstract

Given the ubiquity of charts as a data analysis, visualization, and decision-making tool across industries and sciences, there has been a growing interest in developing pre-trained foundation models as well as general purpose instruction-tuned models for chart understanding and reasoning. However, existing methods suffer crucial drawbacks across two critical axes affecting the performance of chart representation models: they are trained on data generated from underlying data tables of the charts, ignoring the visual trends and patterns in chart images, and use weakly aligned vision-language backbone models for domain-specific training, limiting their generalizability when encountering charts in the wild. We address these important drawbacks and introduce ChartGemma, a novel chart understanding and reasoning model developed over PaliGemma. Rather than relying on underlying data tables, ChartGemma is trained on instruction-tuning data generated directly from chart images, thus capturing both high-level trends and low-level visual information from a diverse set of charts. Our simple approach achieves state-of-the-art results across $5$ benchmarks spanning chart summarization, question answering, and fact-checking, and our elaborate qualitative studies on real-world charts show that ChartGemma generates more realistic and factually correct summaries compared to its contemporaries. We release the code, model checkpoints, dataset, and demos at https://github.com/vis-nlp/ChartGemma.