Using an LLM to Help With Code Understanding

TL;DR

This paper explores an IDE plugin that integrates an LLM to assist developers in understanding code through natural language explanations, API details, and contextual prompts, showing it improves task completion over web search.

Contribution

Introduces a novel IDE plugin leveraging LLMs for code understanding without explicit prompts, evaluated through a user study demonstrating its effectiveness.

Findings

Plugin aids task completion more than web search

Usage and perceived usefulness vary between students and professionals

In-IDE prompt-less interaction with LLMs is promising

Abstract

Understanding code is challenging, especially when working in new and complex development environments. Code comments and documentation can help, but are typically scarce or hard to navigate. Large language models (LLMs) are revolutionizing the process of writing code. Can they do the same for helping understand it? In this study, we provide a first investigation of an LLM-based conversational UI built directly in the IDE that is geared towards code understanding. Our IDE plugin queries OpenAI's GPT-3.5-turbo model with four high-level requests without the user having to write explicit prompts: to explain a highlighted section of code, provide details of API calls used in the code, explain key domain-specific terms, and provide usage examples for an API. The plugin also allows for open-ended prompts, which are automatically contextualized to the LLM with the program being edited. We evaluate this system in a user study with 32 participants, which confirms that using our plugin can aid task completion more than web search. We additionally provide a thorough analysis of the ways developers use, and perceive the usefulness of, our system, among others finding that the usage and benefits differ between students and professionals. We conclude that in-IDE prompt-less interaction with LLMs is a promising future direction for tool builders.