arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.04870cs.FLcs.AIcs.LGcs.LO
收藏

Lemur:在自动化程序验证中集成大型语言模型

Lemur: Integrating Large Language Models in Automated Program Verification

Stanford University(斯坦福大学);VMware Research(威睿研究院);VMware by Broadcom(博通旗下威睿公司)

Haoze Wu, Clark Barrett, Nina Narodytska

AI总结:

本文提出一种将大型语言模型与自动化推理器结合用于自动化程序验证的通用方法,将其形式化为一组转换规则并证明其可靠性,在合成与竞赛基准上取得实际改进。

摘要:

LLM展现出的代码理解能力引发了它们能否用于自动化程序验证的问题,该任务需要对程序属性进行高级抽象推理,这对验证工具极具挑战性。我们提出了一种通用方法,将LLM与自动化推理器的能力结合用于自动化程序验证。我们将该方法形式化描述为一组转换规则,并证明了其可靠性。我们将该演算实例化为一个可靠的自动化验证程序,并在一组合成与竞赛基准上展示了实际的改进。

英文摘要:

The demonstrated code-understanding capability of LLMs raises the question of whether they can be used for automated program verification, a task that demands high-level abstract reasoning about program properties that is challenging for verification tools. We propose a general methodology to combine the power of LLMs and automated reasoners for automated program verification. We formally describe this methodology as a set of transition rules and prove its soundness. We instantiate the calculus as a sound automated verification procedure and demonstrate practical improvements on a set of synthetic and competition benchmarks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑