arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.25804cs.CL
收藏

RealChart2Code:通过真实数据和多任务评估推进图表到代码生成

RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation

USTC(中国科学技术大学);THU(清华大学);CUHK(香港中文大学);UCAS(中国科学院大学);CASIA(中国科学院自动化研究所);BNU(北京师范大学);BUPT(北京邮电大学);BIT(北京理工大学);PKU(北京大学)
Jiajun Zhang, Yuying Li, Zhixun Li, Xingyu Guo, Jingzhuo Wu, Leqi Zheng, Yiran Yang, Jianke Zhang, Qingbin Li, Shannan Yan, Zhetong Li, Changguo Jia, Junfei Wu,… 展开作者

Jiajun Zhang, Yuying Li, Zhixun Li, Xingyu Guo, Jingzhuo Wu, Leqi Zheng, Yiran Yang, Jianke Zhang, Qingbin Li, Shannan Yan, Zhetong Li, Changguo Jia, Junfei Wu, Zilei Wang, Qiang Liu, Liang Wang

AI总结:

本文提出RealChart2Code基准,通过真实数据和多任务评估,评估VLMs在复杂图表生成中的性能,揭示其在多面板图表上的局限性。

摘要:

本文提出RealChart2Code基准,通过真实数据和多任务评估,评估VLMs在复杂图表生成中的性能,揭示其在多面板图表上的局限性。

英文摘要:

Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains. However, their ability to replicate complex, multi-panel visualizations from real-world data remains largely unassessed. To address this gap, we introduce \textbf{\texttt{RealChart2Code}}, a new large-scale benchmark with over 2,800 instances grounded in authentic datasets and featuring tasks with clear analytical intent. Crucially, it is the first benchmark to systematically evaluate chart generation from large-scale raw data and assess iterative code refinement in a multi-turn conversational setting. Our comprehensive evaluation of 14 leading VLMs on \texttt{RealChart2Code} reveals significant performance degradation compared to simpler benchmarks, highlighting their struggles with complex plot structures and authentic data. Our analysis uncovers a substantial performance gap between proprietary and open-weight models and confirms that even state-of-the-art VLMs often fail to accurately replicate intricate, multi-panel charts. These findings provide valuable insights into the current limitations of VLMs and guide future research directions. We release the benchmark and code at \url{https://github.com/Speakn0w/RealChart2Code}.

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。

↑