Leveraging Print Debugging to Improve Code Generation in Large Language Models

TL;DR

This paper introduces a print debugging technique for large language models to enhance their code generation capabilities, especially for complex problems, showing significant improvements over traditional debugging methods.

Contribution

It presents a novel in-context learning approach using print debugging for LLMs, with empirical validation on Leetcode problems demonstrating improved performance.

Findings

Outperforms rubber duck debugging on Leetcode problems

Achieves 1.5% improvement on easy problems

Achieves 17.9% improvement on medium problems

Abstract

Large language models (LLMs) have made significant progress in code generation tasks, but their performance in tackling programming problems with complex data structures and algorithms remains suboptimal. To address this issue, we propose an in-context learning approach that guides LLMs to debug by using a "print debugging" method, which involves inserting print statements to trace and analysing logs for fixing the bug. We collect a Leetcode problem dataset and evaluate our method using the Leetcode online judging system. Experiments with GPT-4 demonstrate the effectiveness of our approach, outperforming rubber duck debugging in easy and medium-level Leetcode problems by 1.5% and 17.9%.