CodeSift: An LLM-Based Reference-Less Framework for Automatic Code Validation

TL;DR

CodeSift is an innovative LLM-based framework that automatically validates code correctness without execution or reference code, significantly reducing validation effort and outperforming existing methods across multiple datasets.

Contribution

It introduces a reference-less, LLM-driven validation framework that enhances efficiency and accuracy in code correctness assessment compared to prior approaches.

Findings

Outperforms state-of-the-art code evaluation methods

Aligns well with human preferences in code validation

Effective across multiple datasets and programming languages

Abstract

The advent of large language models (LLMs) has greatly facilitated code generation, but ensuring the functional correctness of generated code remains a challenge. Traditional validation methods are often time-consuming, error-prone, and impractical for large volumes of code. We introduce CodeSift, a novel framework that leverages LLMs as the first-line filter of code validation without the need for execution, reference code, or human feedback, thereby reducing the validation effort. We assess the effectiveness of our method across three diverse datasets encompassing two programming languages. Our results indicate that CodeSift outperforms state-of-the-art code evaluation methods. Internal testing conducted with subject matter experts reveals that the output generated by CodeSift is in line with human preference, reinforcing its effectiveness as a dependable automated code validation tool.