GoT-CQA: Graph-of-Thought Guided Compositional Reasoning for Chart Question Answering
This addresses the problem of multi-modal reasoning in chart analysis for applications like business data analysis, though it appears incremental as it builds on existing CQA frameworks.
The paper tackles the challenge of complex reasoning in Chart Question Answering (CQA) by proposing GoT-CQA, a Graph-of-Thought guided compositional reasoning model, which achieves outstanding performance on ChartQA and PlotQA-D datasets, particularly in complex human-written and reasoning questions.
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.