paper-with-me

Papers

SIMPLOT: Enhancing Chart Question Answering by Distilling Essentials

2024-02-22 · Wonjoong Kim, Sangwu Park, Yeonjun In, Seokwon Han, Chanyoung Park

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.

📄 PDF Abstract BibTeX arXiv:2405.00021

Code (1)

sangwu99/simplot 공식 구현 pytorch

Tasks

Chart Question AnsweringLanguage ModelingLanguage ModellingLarge Language ModelLogical ReasoningQuestion AnsweringTable Extraction

Similar Papers 제목 키워드 기반

VProChart: Answering Chart Question through Visual Perception Alignment Agent and Programmatic Solution Reasoning

2024-09-03 · Muye Huang, Lingling Zhang, Lai Han, Wenjun Wu 외

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 o…

Chart Question AnsweringData VisualizationLogical ReasoningQuestion Answering

Enhancing Question Answering on Charts Through Effective Pre-training Tasks

2024-06-14 · Ashim Gupta, Vivek Gupta, Shuo Zhang, Yujie He 외

To completely understand a document, the use of textual information is not enough. Understanding visual cues, such as layouts and charts, is also required. While the current state-of-the-art approaches for document under…

document understandingOptical Character Recognition (OCR)Question Answering

FlowVQA: Mapping Multimodal Logic in Visual Question Answering with Flowcharts

2024-06-27 · Shubhankar Singh, Purvi Chaurasia, Yerram Varun, Pranshu Pandya 외

Existing benchmarks for visual question answering lack in visual grounding and complexity, particularly in evaluating spatial reasoning skills. We introduce FlowVQA, a novel benchmark aimed at assessing the capabilities …

Decision MakingLogical ReasoningQuestion AnsweringSpatial Reasoning+2

Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question Answering

2025-03-23 · Zixin Chen, Sicheng Song, Kashun Shum, Yanna Lin 외

Misleading chart visualizations, which intentionally manipulate data representations to support specific claims, can distort perceptions and lead to incorrect conclusions. Despite decades of research, misleading visualiz…

BenchmarkingChart Question AnsweringMultiple-choiceQuestion Answering

Chart Question Answering: State of the Art and Future Directions

2022-05-08 · Enamul Hoque, Parsa Kavehzadeh, Ahmed Masry

Information visualizations such as bar charts and line charts are very common for analyzing data and discovering critical insights. Often people analyze charts to answer questions that they have in mind. Answering such q…

Chart Question AnsweringQuestion Answering