Sketch Then Generate: Providing Incremental User Feedback And Guiding LLM Code Generation Through Language-oriented Code Sketches

Zhu-tian Chen, Xiong Zeyu, Yao Xiaoshuo, Glassman Elena. Arxiv 2024

[Paper]    
Applications Prompting RAG Reinforcement Learning

Crafting effective prompts for code generation or editing with Large Language Models (LLMs) is not an easy task. Particularly, the absence of immediate, stable feedback during prompt crafting hinders effective interaction, as users are left to mentally imagine possible outcomes until the code is generated. In response, we introduce Language-Oriented Code Sketching, an interactive approach that provides instant, incremental feedback in the form of code sketches (i.e., incomplete code outlines) during prompt crafting. This approach converts a prompt into a code sketch by leveraging the inherent linguistic structures within the prompt and applying classic natural language processing techniques. The sketch then serves as an intermediate placeholder that not only previews the intended code structure but also guides the LLM towards the desired code, thereby enhancing human-LLM interaction. We conclude by discussing the approach’s applicability and future plans.

Similar Work