SynChart:从语言模型合成图表
SynChart: Synthesizing Charts from Language Models
AI总结:
本研究探索仅使用LLMs生成数据,构建了包含约400万图像和7500万注释的大规模图表数据集SynChart,并训练了4.2B图表专家模型,在ChartQA任务上超越GPT-4V,达到接近GPT-4O的性能。
摘要:
随着GPT-4V(O)的发布,其在为多模态任务生成伪标签方面的应用变得非常流行。然而,如何从其基础大型语言模型(LLMs)构建此类高级模型仍是一个秘密。本研究探索了仅使用LLMs进行数据生成的潜力,并开发了专注于图表理解的具有竞争力的多模态模型。我们构建了一个大规模图表数据集SynChart,包含约400万张多样化图表图像和超过7500万条密集注释,包括数据表、代码、描述和问答集。我们使用该数据集训练了一个4.2B的图表专家模型,在ChartQA任务上取得了接近GPT-4O的性能,超越了GPT-4V。
英文摘要:
With the release of GPT-4V(O), its use in generating pseudo labels for multi-modality tasks has gained significant popularity. However, it is still a secret how to build such advanced models from its base large language models (LLMs). This work explores the potential of using LLMs alone for data generation and develop competitive multi-modality models focusing on chart understanding. We construct a large-scale chart dataset, SynChart, which contains approximately 4 million diverse chart images with over 75 million dense annotations, including data tables, code, descriptions, and question-answer sets. We trained a 4.2B chart-expert model using this dataset and achieve near-GPT-4O performance on the ChartQA task, surpassing GPT-4V.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。