arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.05216cs.IRcs.AImath.HO
收藏

对900万条数学定理进行语义检索

Semantic Search over 9 Million Mathematical Theorems

Math AI Lab, University of Washington, Seattle, United States(数学AI实验室,华盛顿大学,西雅图,美国);Department of Mathematics, University of Washington, Seattle, United States(数学系,华盛顿大学,西雅图,美国);Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, United States(保罗·G·艾伦计算机科学与工程学院,华盛顿大学,西雅图,美国);Lake Washington High School, Kirkland, United States(拉克华盛顿高中, Kirkland,美国);Department of Applied and Computational Mathematical Sciences, University of Washington, Seattle, United States(应用与计算数学科学系,华盛顿大学,西雅图,美国)

Luke Alexander, Eric Leonen, Sophie Szeto, Artemii Remizov, Ignacio Tejeda, Jarod Alper, Giovanni Inchiostro, Vasily Ilin

AI总结:

本文提出了一种大规模语义检索方法,针对920万条数学定理进行高效检索,显著提升了定理和论文的检索效果。

摘要:

在数学结果的搜索仍然困难:现有的大多数工具检索整篇论文,而数学家和定理证明代理往往寻求特定的定理、引理或命题来回答查询。尽管语义搜索取得了快速进展,但其在大型、高度技术性的语料库(如研究级数学定理)上的行为仍缺乏深入了解。在本工作中,我们引入并研究了大规模语义定理检索,基于从arXiv和其他七个来源提取的统一语料库,包含920万条定理陈述,代表目前公开可用的最大人类撰写的、研究级定理语料库。我们为每个定理提供一个简短的自然语言描述作为检索表示,并系统分析了表示上下文、语言模型选择、嵌入模型和提示策略如何影响检索质量。在由专业数学家撰写的经过精心编排的定理搜索查询集上,我们的方法在定理级和论文级检索上均显著优于现有基线,证明了大规模语义定理搜索的可行性和有效性。该项目页面、搜索工具、数据集、REST API和MCP服务器均可在theoremsearch.com上获得。

英文摘要:

Searching for mathematical results remains difficult: most existing tools retrieve entire papers, while mathematicians and theorem-proving agents often seek a specific theorem, lemma, or proposition that answers a query. While semantic search has seen rapid progress, its behavior on large, highly technical corpora such as research-level mathematical theorems remains poorly understood. In this work, we introduce and study semantic theorem retrieval at scale over a unified corpus of $9.2$ million theorem statements extracted from arXiv and seven other sources, representing the largest publicly available corpus of human-authored, research-level theorems. We represent each theorem with a short natural-language description as a retrieval representation and systematically analyze how representation context, language model choice, embedding model, and prompting strategy affect retrieval quality. On a curated evaluation set of theorem-search queries written by professional mathematicians, our approach substantially improves both theorem-level and paper-level retrieval compared to existing baselines, demonstrating that semantic theorem search is feasible and effective at web scale. The project page, search tool, dataset, REST API, and MCP server are available at theoremsearch.com.

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。

↑