让大模型更懂数据探索，自动选对上下文
NoteEx: Interactive Visual Context Manipulation for LLM-Assisted Exploratory Data Analysis in Computational Notebooks
- 用语义可视化显化分析流程，帮助用户理清思路
- 用户研究显示准确率提升，减少重复提问
- 适合在笔记本中做数据分析的科研与工程师
计算笔记本已成为探索性数据分析（EDA）的常用工具，借助基于大模型的代码生成与结果解释能力。有效的大模型辅助依赖于选择有意义的上下文——即回答问题所需的最小代码、数据或输出单元格集合。随着笔记本变长且混乱，用户容易迷失分析逻辑，难以筛选合适的上下文，导致挫败感和繁琐的提示工程。我们开展了一项形成性研究（n=6），揭示了大模型上下文选择与心智模型维护中的挑战。为此，我们提出 NoteEx，一个 JupyterLab 插件，通过语义可视化呈现 EDA 流程，使分析师能够外化心智模型、定义分析依赖，并交互式选择任务相关的上下文供大模型使用。一项用户研究（n=12）对比基线表明，NoteEx 显著提升了心智模型保持与上下文选择能力，从而获得更准确、相关的大模型响应。
原文摘要 · Abstract (English)
Computational notebooks have become popular for Exploratory Data Analysis (EDA), augmented by LLM-based code generation and result interpretation. Effective LLM assistance hinges on selecting informative context -- the minimal set of cells whose code, data, or outputs suffice to answer a prompt. As notebooks grow long and messy, users can lose track of the mental model of their analysis. They thus fail to curate appropriate contexts for LLM tasks, causing frustration and tedious prompt engineering. We conducted a formative study (n=6) that surfaced challenges in LLM context selection and mental model maintenance. Therefore, we introduce NoteEx, a JupyterLab extension that provides a semantic visualization of the EDA workflow, allowing analysts to externalize their mental model, specify analysis dependencies, and enable interactive selection of task-relevant contexts for LLMs. A user study (n=12) against a baseline shows that NoteEx improved mental model retention and context selection, leading to more accurate and relevant LLM responses.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。