Dashboard2Code：在重建交互式仪表板上评估多模态模型
Dashboard2Code: Evaluating Multimodal Models on Reconstructing Interactive Dashboards
AI总结：
研究多模态模型在交互式仪表板重建任务，介绍Dashboard2Code任务，提出DashboardMimic基准及自动化评估框架，实验发现开源与闭源模型在此任务上有差距。
摘要：
自动数据可视化生成借助多模态大语言模型快速发展，但现有工作多关注静态图表，忽视交互式仪表板。我们引入Dashboard2Code任务，它要求模型主动探索交互式仪表板，获取并整合交互反馈以生成代码重现目标仪表板。为支持全面评估，我们展示了DashboardMimic，首个针对Dashboard2Code的Plotly+Dash基准，包含180个精心设计且经人工验证的仪表板-代码对，涵盖三个难度级别和八种常见的现实世界交互模式。我们进一步提出一个针对仪表板的自动化评估框架，该框架将代码语义分析与基于动态交互的测试相结合，以评估视觉和交互一致性，与人类判断显示出高度一致性。在一系列开源和闭源多模态模型上的实验表明，即使是最强的系统在高复杂性仪表板上也面临困难，并且在Dashboard2Code任务上，开源模型和闭源模型之间仍存在巨大的性能差距。
英文摘要：
Automatic data visualization generation has advanced rapidly with multi-modal large language models, yet existing efforts largely focus on static charts and overlook the interactive dashboards commonly used for real-world data exploration. We introduce Dashboard2Code, a novel task that requires a model to proactively explore an interactive dashboard, acquire and integrate feedback from its own interactions (e.g., clicking and filtering), and generate code that reproduces the target dashboard. To support comprehensive evaluation, we present DashboardMimic, the first Plotly+Dash benchmark for Dashboard2Code, comprising 180 carefully designed and manually verified dashboard-code pairs spanning three difficulty levels and covering eight common real-world interaction patterns. We further propose an automated evaluation framework tailored to dashboards that combines code semantic analysis with dynamic interaction-based testing to assess visual and interaction consistency, showing strong agreement with human judgments. Experiments across a range of open- and closed-source multi-modal models reveal that even the strongest systems struggle on high-complexity dashboards and that a substantial performance gap remains between open-source and closed-source models on the Dashboard2Code task.
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。
