End-to-End Chart Summarization via Visual Chain-of-Thought in Vision-Language Models

TL;DR

This paper presents a novel end-to-end visual chain-of-thought approach for chart summarization using large vision-language models, significantly improving automatic and human evaluation metrics over previous methods.

Contribution

It introduces a visual Chain-of-Thought mechanism with instruction fine-tuning for end-to-end chart summarization, eliminating explicit parsing modules and enhancing reasoning capabilities.

Findings

Outperforms state-of-the-art baselines on Chart-Sum-QA dataset

Achieves higher scores on BLEU, BLEURT, CIDEr, and CS metrics

Demonstrates superior reasoning and matching in human evaluations

Abstract

Automated chart summarization is crucial for enhancing data accessibility and enabling efficient information extraction from visual data. While recent advances in visual-language models (VLMs) have demonstrated promise, existing methods often suffer from limitations in matching the generated summary to the chart data and in reasoning about complex chart patterns. This paper introduces End-to-End Visual Chain-of-Thought (V-CoT) for chart summarization, a novel approach optimized for Large Vision-Language Models (LVLMs). Our method directly trains an LVLM to process chart images and generate textual summaries in an end-to-end fashion, eliminating the need for explicit chart parsing modules. We incorporate a visual Chain-of-Thought mechanism through instruction fine-tuning, implicitly guiding the LVLM to perform visual reasoning steps during summary generation. Evaluated on the large-scale Chart-Sum-QA dataset, our V-CoT method significantly outperforms state-of-the-art baselines across a range of automatic metrics, including BLEU, BLEURT, CIDEr, and CS, and demonstrates superior matching degree and reasoning correctness in human evaluations. Ablation studies and detailed analyses further validate the effectiveness and robustness of our proposed approach, establishing a new benchmark for end-to-end chart summarization.