通过视觉对齐与程序化推理，提升图表问答的准确率
VProChart: Answering Chart Question through Visual Perception Alignment Agent and Programmatic Solution Reasoning
- 用人类视觉规律对齐图表元素，增强上下文理解
- 将自然语言问题转为结构化程序，实现精准推理
- 在ChartQA和PlotQA上超越现有方法，适合复杂图表分析
图表在教育、科研和商业等领域广泛用于数据可视化。图表问答（CQA）是一项新兴任务，旨在自动解析和推理图表中的数据。然而，图表图像本身难以理解，相关问题常涉及复杂的逻辑与数值推理，限制了现有模型的表现。本文提出VProChart，一个融合轻量级视觉感知对齐代理（VPAgent）与程序化求解推理的方法。VPAgent基于人类视觉感知原理对齐并建模图表元素，提升对图表上下文的理解。程序化求解推理利用大语言模型（LLMs）将自然语言推理问题转化为结构化解决方案程序，支持精确的数值与逻辑推理。在ChartQA和PlotQA等基准数据集上的大量实验表明，VProChart显著优于现有方法，展现出强大的图表理解与推理能力。
原文摘要 · Abstract (English)
Charts are widely used for data visualization across various fields, including education, research, and business. Chart Question Answering (CQA) is an emerging task focused on the automatic interpretation and reasoning of data presented in charts. However, chart images are inherently difficult to interpret, and chart-related questions often involve complex logical and numerical reasoning, which hinders the performance of existing models. This paper introduces VProChart, a novel framework designed to address these challenges in CQA by integrating a lightweight Visual Perception Alignment Agent (VPAgent) and a Programmatic Solution Reasoning approach. VPAgent aligns and models chart elements based on principles of human visual perception, enhancing the understanding of chart context. The Programmatic Solution Reasoning approach leverages large language models (LLMs) to transform natural language reasoning questions into structured solution programs, facilitating precise numerical and logical reasoning. Extensive experiments on benchmark datasets such as ChartQA and PlotQA demonstrate that VProChart significantly outperforms existing methods, highlighting its capability in understanding and reasoning with charts.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。