SGCR: A Specification-Grounded Framework for Trustworthy LLM Code Review

The article introduces a framework (SGCR) for improving the trustworthiness of Large Language Model (LLM) based code review. The focus is on grounding the review process in specifications, which likely aims to enhance the reliability and accuracy of the code analysis performed by LLMs. The source being ArXiv suggests this is a research paper.