Bridging LLM-Generated Code and Requirements: Reverse Generation technique and SBC Metric for Developer Insights

TL;DR

This paper presents a novel SBC scoring method that uses reverse generation to evaluate AI-generated code by reconstructing requirements and comparing them with original specifications, improving developer insights.

Contribution

Introduces the SBC score, a new evaluation metric combining semantic similarity, BLEU, and completeness, for better assessment of LLM-generated code quality.

Findings

SBC score correlates better with human judgment than traditional metrics.

Reverse generation effectively identifies missing features and hallucinations.

The approach enhances developer understanding of AI-generated code.

Abstract

The rise of Large Language Models (LLMs) in software engineering, particularly in code generation, has garnered significant attention. However, assessing the quality of AI-generated code remains a challenge due to the inherent complexity of programming tasks and the lack of robust evaluation metrics that align well with human judgment. Traditional token-based metrics such as BLEU and ROUGE, while commonly used in natural language processing, exhibit weak correlations with human assessments in code intelligence and verification tasks. Furthermore, these metrics are primarily research focused and are not designed for seamless integration into the software development lifecycle, limiting their practical utility for developers seeking to improve code quality and security. AI-assisted coding has been shown to be more beneficial for senior developers, as they possess the expertise to critically evaluate the generated code for correctness, completeness, and compliance. In contrast, junior developers may struggle to identify hallucinations, missing functionality, or incorrect logic in AI-generated code. To bridge this gap, This paper introduces a novel scoring mechanism called the SBC score, which is based on a reverse generation technique that leverages the natural language generation capabilities of LLMs. Unlike direct code analysis, our approach reconstructs system requirements from AI-generated code and compares them with the original specifications to quantify accuracy. The SBC score combines semantic similarity, BLEU, and completeness analysis, providing actionable insights to developers by highlighting missing features and hallucinations. Our code and datasets are available on GitHub