ChartThinker：一种用于优化图表摘要的上下文思维链方法
ChartThinker: A Contextual Chain-of-Thought Approach to Optimized Chart Summarization
AI总结：
针对图表摘要中视觉-语言匹配与推理能力的不足，本研究构建大规模图表-标题对数据集，并提出基于思维链与上下文检索的方法 ChartThinker，在7项指标上超越8个基线模型。
摘要：
数据可视化是呈现数据并挖掘其有价值见解的关键手段。通过自然语言处理技术，图表摘要任务能够促进对图表的深入数据分析。然而，现有方法在视觉-语言匹配和推理能力方面仍存在明显不足。为了解决这些局限性，本研究构建了一个包含全面图表-标题对的大规模数据集，并为每个图表设计了微调指令。得益于该数据集涵盖的广泛主题和视觉风格，从训练数据的角度可以实现更好的匹配度。此外，我们提出了一种创新的图表摘要方法 ChartThinker，该方法基于思维链和上下文检索策略合成深度分析，旨在提高生成摘要的逻辑连贯性和准确性。基于精心整理的数据集，我们训练的模型在图表摘要任务中表现出卓越的性能，在7项评估指标上超越了8个最先进的模型。我们的数据集和代码已公开访问。
英文摘要：
Data visualization serves as a critical means for presenting data and mining its valuable insights. The task of chart summarization, through natural language processing techniques, facilitates in-depth data analysis of charts. However, there still are notable deficiencies in terms of visual-language matching and reasoning ability for existing approaches. To address these limitations, this study constructs a large-scale dataset of comprehensive chart-caption pairs and fine-tuning instructions on each chart. Thanks to the broad coverage of various topics and visual styles within this dataset, better matching degree can be achieved from the view of training data. Moreover, we propose an innovative chart summarization method, ChartThinker, which synthesizes deep analysis based on chains of thought and strategies of context retrieval, aiming to improve the logical coherence and accuracy of the generated summaries. Built upon the curated datasets, our trained model consistently exhibits superior performance in chart summarization tasks, surpassing 8 state-of-the-art models over 7 evaluation metrics. Our dataset and codes are publicly accessible.
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。
