BISCUIT: Scaffolding LLM-Generated Code with Ephemeral UIs in Computational Notebooks
This addresses usability challenges for programmers using LLM-based code generation in machine learning tutorials, though it is an incremental improvement focused on workflow enhancement.
The paper tackles the problem of programmers struggling to understand and work with LLM-generated code in computational notebooks by introducing BISCUIT, a JupyterLab extension that adds an ephemeral UI step to scaffold code generation, and found in a user study with 10 novices that it aids understanding, reduces prompt engineering complexity, and enables exploration.
Programmers 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 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 a user study where 10 novices used BISCUIT for machine learning tutorials, we found that BISCUIT offers users representations 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.