SIMPLOT: Enhancing Chart Question Answering by Distilling Essentials

TL;DR

SIMPLOT improves chart question answering by distilling essential information from complex charts, enabling more accurate reasoning without extra annotations, through a two-step process of mimicking simple plots and reasoning based on extracted tables.

Contribution

The paper introduces SIMPLOT, a novel method that extracts only essential chart elements for reasoning, enhancing accuracy without additional annotations or datasets.

Findings

Effective in extracting essential chart information

Improves reasoning accuracy in chart question answering

Demonstrates superior performance over previous models

Abstract

Recently, interpreting complex charts with logical reasoning has emerged as challenges due to the development of vision-language models. A prior state-of-the-art (SOTA) model has presented an end-to-end method that leverages the vision-language model to convert charts into table format utilizing Large Language Model (LLM) for reasoning. However, unlike natural images, charts contain a mix of essential and irrelevant information required for chart reasoning, and we discover that this characteristic can lower the performance of chart-to-table extraction. In this paper, we introduce SIMPLOT, a method designed to extract only the elements necessary for chart reasoning. The proposed method involves two steps: 1) training to mimic a simple plot that contains only the essential information from a complex chart for table extraction, followed by 2) performing reasoning based on the table. Our model enables accurate chart reasoning without the need for additional annotations or datasets, and its effectiveness is demonstrated through various experiments. Furthermore, we propose a novel prompt mimicking how human interpret charts for more accurate reasoning. Our source code is available at https://github.com/sangwu99/Simplot.