ROCODE: Integrating Backtracking Mechanism and Program Analysis in Large Language Models for Code Generation

TL;DR

ROCODE enhances large language models for code generation by integrating backtracking and program analysis, enabling early error detection and correction during generation, which significantly improves accuracy and efficiency.

Contribution

This paper introduces ROCODE, a novel framework combining backtracking and program analysis to detect and correct errors during code generation in LLMs, reducing errors and resource wastage.

Findings

Achieves 99.1% compilation pass rate.

Improves test pass rate by up to 23.8%.

Reduces token cost by 19.3%.

Abstract

Large language models (LLMs) have achieved impressive performance in code generation recently, offering programmers revolutionary assistance in software development. However, due to the auto-regressive nature of LLMs, they are susceptible to error accumulation during code generation. Once an error is produced, LLMs can merely continue to generate the subsequent code conditioned on it, given their inability to adjust previous outputs. Existing LLM-based approaches typically consider post-revising after code generation, leading to the challenging resolution of accumulated errors and the significant wastage of resources. Ideally, LLMs should rollback and resolve the occurred error in time during code generation, rather than proceed on the basis of the error and wait for post-revising after generation. In this paper, we propose ROCODE, which integrates the backtracking mechanism and program analysis into LLMs for code generation. Specifically, we employ program analysis to perform incremental error detection during the generation process. When an error is detected, the backtracking mechanism is triggered to priming rollback strategies and constraint regeneration, thereby eliminating the error early and ensuring continued generation on the correct basis. Experiments on multiple code generation benchmarks show that ROCODE can significantly reduce the errors generated by LLMs, with a compilation pass rate of 99.1%. The test pass rate is improved by up to 23.8% compared to the best baseline approach. Compared to the post-revising baseline, the token cost is reduced by 19.3%. Moreover, our approach is model-agnostic and achieves consistent improvements across nine representative LLMs.