METAMON: Finding Inconsistencies between Program Documentation and Behavior using Metamorphic LLM Queries

TL;DR

METAMON is a novel approach that leverages test generation and large language models to automatically detect inconsistencies between code documentation and actual program behavior, improving code understanding and quality.

Contribution

This paper introduces METAMON, combining search-based test generation with LLM reasoning to automatically identify documentation-code inconsistencies, a task previously reliant on manual effort.

Findings

Achieves 0.72 precision in classifying inconsistencies

Recalls 0.48 of actual inconsistencies

Evaluated on 9,482 code-documentation pairs from open-source projects

Abstract

Code documentation can, if written precisely, help developers better understand the code they accompany. However, unlike code, code documentation cannot be automatically verified via execution, potentially leading to inconsistencies between documentation and the actual behavior. While such inconsistencies can be harmful for the developer's understanding of the code, checking and finding them remains a costly task due to the involvement of human engineers. This paper proposes METAMON, which uses an existing search-based test generation technique to capture the current program behavior in the form of test cases, and subsequently uses LLM-based code reasoning to identify the generated regression test oracles that are not consistent with the program specifications in the documentation. METAMON is supported in this task by metamorphic testing and self-consistency. An empirical evaluation against 9,482 pairs of code documentation and code snippets, generated using five open-source projects from Defects4J v2.0.1, shows that METAMON can classify the code-and-documentation inconsistencies with a precision of 0.72 and a recall of 0.48.