math-PVS:一个将科学出版物映射到PVS理论的大语言模型框架
math-PVS: A Large Language Model Framework to Map Scientific Publications to PVS Theories
AI总结:
本文提出math-PVS框架,将大语言模型与PVS证明助手结合,自动从研究论文中提取并形式化数学定理,以弥补LLMs推理不足并支持学术审阅与发现。
摘要:
随着人工智能(AI)在各类应用中得到更广泛的采用,它在数学发现方面具有巨大的潜力,例如引导猜想生成、构造反例、辅助数学形式化以及发现不同数学领域之间的联系等。虽然先前的工作已经利用计算机进行穷举式数学证明搜索,但近期基于大语言模型(LLMs)的努力致力于将计算平台定位为数学研究过程中的共同贡献者。尽管当前LLMs在逻辑和数学任务上存在局限性,但将定理证明系统与基础模型相融合的兴趣日益增长。本工作研究了LLMs在形式化高级数学概念方面的适用性,并提出了一个能够批判性审阅和检查研究论文中数学推理的框架。鉴于LLMs在推理方面的已知不足,我们的方法将证明助手(特别是PVS)的能力与LLMs协同结合,从而在学术论文的文本描述与PVS中的形式化规范之间架起桥梁。通过利用PVS环境,并结合数据摄取与转换机制,我们设想了一个名为math-PVS的自动化流程,用于从研究论文中提取并形式化数学定理,为学术审阅与发现提供一种创新工具。
英文摘要:
As artificial intelligence (AI) gains greater adoption in a wide variety of applications, it has immense potential to contribute to mathematical discovery, by guiding conjecture generation, constructing counterexamples, assisting in formalizing mathematics, and discovering connections between different mathematical areas, to name a few. While prior work has leveraged computers for exhaustive mathematical proof search, recent efforts based on large language models (LLMs) aspire to position computing platforms as co-contributors in the mathematical research process. Despite their current limitations in logic and mathematical tasks, there is growing interest in melding theorem proving systems with foundation models. This work investigates the applicability of LLMs in formalizing advanced mathematical concepts and proposes a framework that can critically review and check mathematical reasoning in research papers. Given the noted reasoning shortcomings of LLMs, our approach synergizes the capabilities of proof assistants, specifically PVS, with LLMs, enabling a bridge between textual descriptions in academic papers and formal specifications in PVS. By harnessing the PVS environment, coupled with data ingestion and conversion mechanisms, we envision an automated process, called \emph{math-PVS}, to extract and formalize mathematical theorems from research papers, offering an innovative tool for academic review and discovery.
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。