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
备注:
theoremsearch.com
发表信息:
ICLR 2026 Workshop: Logical Reasoning of Large Language Models
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.
Supervised Typing of Big Graphs using Semantic Embeddings
College of William and Mary(威廉与玛丽学院);University of Virginia(弗吉尼亚大学);Eaton Innovation Center(伊顿创新中心);University of Minnesota(明尼苏达大学);Google(谷歌);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Author(作者大学);Authorship Holdings, Ltd.(作者控股有限公司);YetAuthorCo, Inc.(耶特作者公司);University of Umbhali(翁巴利大学);Institute for Clarity in Documentation(文档清晰度研究所);Brookhaven Laboratories(布鲁克海文实验室);NASA Ames Research Center(美国国家航空航天局艾姆斯研究中心);Palmer Research Laboratories(帕尔默研究实验室)
Health System Scale Semantic Search Across Unstructured Clinical Notes
Department of Biomedical and Health Informatics, Children’s Hospital of Philadelphia(儿童医院哲学学院生物医学与健康信息学系);Google Cloud(谷歌云);Department of Pediatrics, University of Pennsylvania(宾夕法尼亚大学儿科系);Division of Neonatology, Children’s Hospital of Philadelphia(儿童医院哲学学院新生儿科);Division of Human Genetics, Children’s Hospital of Philadelphia(儿童医院哲学学院人类遗传学部)
Growing the Digital Repository of Mathematical Formulae with Generic LaTeX Sources
DRMF的一个初始目标是用基本的正交多项式公式来播种我们的数字纲要。我们使用NIST数学函数数字图书馆(DLMF)的数据作为DRMF项目的初始种子。DLMF输入LaTeX源已经包含了一些使用高度定制的语义LaTeX宏集编码的语义信息。这些宏可以使用LaTeXML转换为内容MathML。在该转换期间,语义被转换为隐式DLMF内容字典。今年,我们开发了一个语义丰富的过程,其目标是从通用的LaTeX源推断语义信息。生成的上下文无关语义信息用于为每个公式构建DRMF公式主页。我们使用Koekoek,Lesky and Swarttouw(KLS)的“Hypergeometric Orthogonal Polynomials and their $q$ -Analogues”(2010)一书中的选定章节以及Koornwinder(KLSadd)积极维护的本书附录来演示此过程。通用输入KLS和KLSadd LaTeX源描述公式的打印表示,但不包含显式语义信息。请访问http://drmf.wmflabs.org。
School of Mathematical Sciences, Peking University(北京大学数学科学学院);Beijing International Center for Mathematical Research, Peking University(北京大学北京国际数学研究中心);IQuest Research(IQuest研究);Beijing International Center for Mathematical Research and the New Cornerstone Science Laboratory, Peking University(北京大学北京国际数学研究中心和新基石科学实验室);Center for Machine Learning Research, Peking University(北京大学机器学习研究中心);Center for Intelligent Computing, Great Bay Institute for Advanced Study, Great Bay University(大亚湾先进研究所智能计算中心);Zhongguancun Academy(中关村学院)
School of Mathematical Sciences, Peking University(北京大学数学科学学院);Beijing International Center for Mathematical Research, Peking University(北京国际数学研究中心(北京大学));Center for Machine Learning Research, Peking University(北京大学机器学习研究中心)