Novices frequently engage with machine learning tutorials in computational notebooks and have been adopting code generation technologies based on large language models (LLMs). However, they encounter difficulties in understanding and working with code produced by LLMs. To mitigate these challenges, we introduce a novel workflow into computational notebooks that augments LLM-based code generation with an additional ephemeral UI step, offering users UI-based scaffolds as an intermediate stage between user prompts and code generation. We present this workflow in BISCUIT, an extension for JupyterLab that provides users with ephemeral UIs generated by LLMs based on the context of their code and intentions, scaffolding users to understand, guide, and explore with LLM-generated code. Through 10 user studies where novices used BISCUIT for machine learning tutorials, we discover that BISCUIT offers user semantic representation of code to aid their understanding, reduces the complexity of prompt engineering, and creates a playground for users to explore different variables and iterate on their ideas. We discuss the implications of our findings for UI-centric interactive paradigm in code generation LLMs.

中文翻译：

---

BISCUIT：在计算笔记本中使用临时 UI 搭建 LLM 生成的代码

新手经常在计算笔记本中学习机器学习教程，并一直在采用基于大型语言模型 (LLM) 的代码生成技术。然而，他们在理解和使用法学硕士生成的代码方面遇到了困难。为了缓解这些挑战，我们在计算笔记本中引入了一种新颖的工作流程，通过额外的临时 UI 步骤来增强基于 LLM 的代码生成，为用户提供基于 UI 的支架作为用户提示和代码生成之间的中间阶段。我们在 BISCUIT 中展示了这个工作流程，BISCUIT 是 JupyterLab 的扩展，它为用户提供由 LLM 基于其代码上下文和意图生成的临时 UI，为用户提供理解、指导和探索 LLM 生成的代码的框架。通过 10 个新手使用 BISCUIT 进行机器学习教程的用户研究，我们发现 BISCUIT 提供了代码的用户语义表示来帮助他们理解，降低了提示工程的复杂性，并为用户创建了一个探索不同变量并迭代他们的想法的游乐场。我们讨论了我们的研究结果对代码生成法学硕士中以 UI 为中心的交互范式的影响。