GoT-CQA: Graph-of-Thought Guided Compositional Reasoning for Chart Question Answering

TL;DR

This paper introduces GoT-CQA, a novel graph-of-thought guided model for chart question answering that enhances complex reasoning capabilities by mimicking human problem-solving processes, leading to superior performance on benchmark datasets.

Contribution

The paper proposes a new graph-of-thought framework for compositional reasoning in chart question answering, improving handling of complex, multi-step reasoning tasks.

Findings

Achieves state-of-the-art results on ChartQA and PlotQA-D datasets.

Excels particularly in complex reasoning and human-like question scenarios.

Demonstrates the effectiveness of graph-of-thought guided reasoning in multi-modal tasks.

Abstract

Chart Question Answering (CQA) aims at answering questions based on the visual chart content, which plays an important role in chart sumarization, business data analysis, and data report generation. CQA is a challenging multi-modal task because of the strong context dependence and complex reasoning requirement. The former refers to answering this question strictly based on the analysis of the visual content or internal data of the given chart, while the latter emphasizes the various logical and numerical reasoning involved in answer prediction process. In this paper, we pay more attention on the complex reasoning in CQA task, and propose a novel Graph-of-Thought (GoT) guided compositional reasoning model called GoT-CQA to overcome this problem. At first, we transform the chart-oriented question into a directed acyclic GoT composed of multiple operator nodes, including localization, numerical and logical operator. It intuitively reflects the human brain's solution process to this question. After that, we design an efficient auto-compositional reasoning framework guided by the GoT, to excute the multi-step reasoning operations in various types of questions. Comprehensive experiments on ChartQA and PlotQA-D datasets show that GoT-CQA achieves outstanding performance, especially in complex human-written and reasoning questions, comparing with the latest popular baselines.