IntelliExplain: Enhancing Conversational Code Generation for Non-Professional Programmers

TL;DR

IntelliExplain improves conversational code generation for non-professional programmers by enhancing explanations and interaction structure, leading to higher success rates and reduced task times in SQL and Python tasks.

Contribution

The paper introduces IntelliExplain, a novel framework that enhances code explanations and interaction structure to make Chat LLMs more accessible for non-experts.

Findings

Higher success rates in SQL and Python tasks

Reduced task completion time

Identified key factors affecting non-professional programmers' experience

Abstract

Chat LLMs such as GPT-3.5-turbo and GPT-4 have shown promise in assisting humans in coding, particularly by enabling them to conversationally provide feedback. However, current approaches assume users have expert debugging skills, limiting accessibility for non-professional programmers. In this paper, we first explore Chat LLMs' limitations in assisting non-professional programmers with coding. Through a formative study, we identify two key elements affecting their experience: the way a Chat LLM explains its generated code and the structure of human-LLM interaction. We then propose IntelliExplain, a new conversational code generation framework with enhanced code explanations and a structured interaction paradigm, which enforces both better code understanding and a more effective feedback loop. In two programming tasks (SQL and Python), IntelliExplain yields significantly higher success rates and reduces task time compared to the vanilla Chat LLM. We also identify several opportunities that remain in effectively offering a chat-based programming experience for non-professional programmers.