WaitGPT：通过实时代码可视化监控和引导数据分析中的对话式 LLM 智能体
WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualization
AI总结：
本文提出 WaitGPT，将 LLM 生成的数据分析代码实时转为逐步交互式可视化，帮助用户监控、验证和修改分析流程，并通过用户研究验证其在错误检测与结果信心方面的提升。
摘要：
大型语言模型（LLM）通过对话式用户界面支持数据分析，OpenAI 的 ChatGPT（正式名称为 Advanced Data Analysis 或 Code Interpreter）即是例证。从本质上讲，LLM 会生成代码以完成各种分析任务。然而，直接展示原始代码可能会掩盖逻辑并妨碍用户验证。为了使用户能够更好地理解并增强对 LLM 所执行分析的控制，我们提出了一种新方法，将 LLM 生成的代码转换为交互式可视化表示。在该方法中，用户可以实时获得 LLM 生成代码的清晰、逐步可视化，从而理解、验证并修改分析中的各个数据操作。我们的设计决策基于一项探究用户实践与挑战的形成性研究（N=8）。我们进一步开发了名为 WaitGPT 的原型，并开展了一项用户研究（N=12）以评估其可用性和有效性。用户研究结果表明，WaitGPT 促进了对 LLM 所执行数据分析的监控和引导，使参与者能够增强错误检测能力，并提高他们对结果的整体信心。
英文摘要：
Large language models (LLMs) support data analysis through conversational user interfaces, as exemplified in OpenAI's ChatGPT (formally known as Advanced Data Analysis or Code Interpreter). Essentially, LLMs produce code for accomplishing diverse analysis tasks. However, presenting raw code can obscure the logic and hinder user verification. To empower users with enhanced comprehension and augmented control over analysis conducted by LLMs, we propose a novel approach to transform LLM-generated code into an interactive visual representation. In the approach, users are provided with a clear, step-by-step visualization of the LLM-generated code in real time, allowing them to understand, verify, and modify individual data operations in the analysis. Our design decisions are informed by a formative study (N=8) probing into user practice and challenges. We further developed a prototype named WaitGPT and conducted a user study (N=12) to evaluate its usability and effectiveness. The findings from the user study reveal that WaitGPT facilitates monitoring and steering of data analysis performed by LLMs, enabling participants to enhance error detection and increase their overall confidence in the results.
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。
