Teaching Large Language Models to Self-Debug

Abstract

Large language models (LLMs) have achieved impressive performance on code generation. However, for complex programming tasks, generating the correct solution in one go becomes challenging, thus some prior works have designed program repair approaches to improve code generation performance. In this work, we propose Self-Debugging, which teaches a large language model to debug its predicted program via few-shot demonstrations. In particular, we demonstrate that Self-Debugging can teach the large language model to perform rubber duck debugging; i.e., without any human feedback on the code correctness or error messages, the model is able to identify its mistakes by investigating the execution results and explaining the generated code in natural language. Self-Debugging achieves the state-of-the-art performance on several code generation benchmarks, including the Spider dataset for text-to-SQL generation, TransCoder for C++-to-Python translation, and MBPP for text-to-Python generation. On the Spider benchmark where there are no unit tests to verify the correctness of predictions, Self-Debugging with code explanation consistently improves the baseline by 2-3%, and improves the prediction accuracy on problems of the hardest level by 9%. On TransCoder and MBPP where unit tests are available, Self-Debugging improves the baseline accuracy by up to 12%. Meanwhile, by leveraging feedback messages and reusing failed predictions, Self-Debugging notably improves sample efficiency, and can match or outperform baseline models that generate more than 10x candidate programs.

Cited by in corpus (10)

• LLM for SoC Security: A Paradigm Shift
• Designing Heterogeneous LLM Agents for Financial Sentiment Analysis
• LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers
• Automating Autograding: Large Language Models as Test Suite Generators for Introductory Programming
• Text-to-OverpassQL: A Natural Language Interface for Complex Geodata Querying of OpenStreetMap
• Large Language Models to the Rescue: Reducing the Complexity in Scientific Workflow Development Using ChatGPT
• Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models
• Flows: Building Blocks of Reasoning and Collaborating AI
• Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk
• Assessing the Latent Automated Program Repair Capabilities of Large Language Models using Round-Trip Translation