跳到正文
arXiv cs.AI· Jan Range, Bj\"orn Schembera, Dominik G\"oddeke·· 2 小时前AI 评分33

通过大语言模型集成让数学知识更可解释、可访问且可互操作

Making Mathematical Knowledge Explainable, Accessible and Interoperable Through Large Language Model Integration

AI 导读

研究者提出通过 Model Context Protocol(MCP)服务器将大语言模型(LLM)与数学模型知识库 MathModDB 集成,该服务器提供向量索引的 schema 检索和基于 Steiner 树的连接规划器,实现自然语言对话式访问。

正文 · 原文

View PDF HTML (experimental)

Abstract:Mathematical models are central to formalizing research problems, yet their documentation often falls short of FAIR principles. Knowledge bases such as the Mathematical Model Database (MathModDB) address this gap by providing curated, semantically rich representations of mathematical models. Built on Wikibase, the same open-source infrastructure underlying Wikidata, MathModDB utilizes Semantic Web technologies to support Linked Open Data, collaborative editing, and the storage of semantically enriched metadata, making it a domain-specific knowledge graph within the broader Wikidata ecosystem. However, access to MathModDB currently requires either navigating a complex web interface or proficiency in SPARQL and Wikibase APIs, posing significant barriers for potential users. In addition, the combination of such curated knowledge bases with actual research data stored, e.g., in Dataverse repository instances, remains a challenge. To overcome these limitations, we propose integrating Large Language Models (LLMs) with MathModDB via a Model Context Protocol (MCP) server that exposes a vector-indexed schema retrieval and Steiner-tree-based join planner, combining dialogue-based natural language interaction with curated, epistemically grounded knowledge. Although instantiated on MathModDB, the architecture can be applied to other Wikibase-based systems. We demonstrate that this approach enables epistemically grounded LLM usage, improves model explainability and accessibility beyond what the standard Wikibase interface offers, and simplifies interoperability with external databases and tools, such as Dataverse data repositories. We illustrate the benefits of combining the accessibility of an LLM with the epistemic safety of a curated knowledge base through the adaptability of the MCP protocol by two use cases.
Comments: Published in Proceedings of the 6th Wikidata Workshop @ ISWC 2026
Subjects: Artificial Intelligence (cs.AI); Digital Libraries (cs.DL)
Cite as: arXiv:2607.24512 [cs.AI]
  (or arXiv:2607.24512v2 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2607.24512

arXiv-issued DOI via DataCite

Submission history

From: Björn Schembera [view email]
[v1] Mon, 27 Jul 2026 14:53:40 UTC (28 KB)
[v2] Wed, 18 Nov 2026 10:05:38 UTC (47 KB)

来源:arXiv cs.AI · arxiv.org