Incorporating natural language input has the potential to improve the capabilities of biomedical data discovery interfaces. However, user interface elements and visualizations are still powerful tools for interacting with data. In our prototype system, YAC, Yet Another Chatbot, we integrate natural language and interactive visualizations. YAC uses a tool-calling multi-agent system to generate declarative output, which is interpreted to render linked interactive visualizations and apply data filters. We also include adjustment widgets, which allow users to directly modify the structured output. Structured text is also generated to clarify user intent, notify users of system boundaries, and explain aspects of the data with live data element links. We conducted a user study with domain experts to surface areas where YAC can be improved. Furthermore we reflect on the capabilities and design of this system with an analysis of its technical dimensions.

翻译：整合自然语言输入有望提升生物医学数据发现界面的能力，但用户界面元素与可视化仍是与数据交互的有力工具。在我们的原型系统YAC（Yet Another Chatbot）中，自然语言与交互式可视化得以融合。YAC采用基于工具调用的多智能体系统生成声明式输出，该输出经解释后可呈现关联的交互式可视化并应用数据筛选。我们还引入调整控件，使用户能够直接修改结构化输出。生成的复合文本可澄清用户意图、提示系统边界，并通过实时数据元素链接解释数据维度。通过与领域专家开展的用户研究，我们揭示了YAC的改进方向。同时，基于技术维度分析，本文对系统的能力与设计进行了反思。