arXiv:2605.09184cs.AIcs.CL2026-05被引 2

用稳定匹配提升本体对齐质量,工具辅助让大模型更懂本体。

Open Ontologies: Tool-Augmented Ontology Engineering with Stable Matching Alignment

  • 通过稳定的一一匹配机制优化本体对齐,提升精度与鲁棒性。
  • 在解剖学赛道上达到F1=0.832,精度高达0.963,显著优于现有方法。
  • 结构化工具接口比直接读取原始本体文件更有效,适合本体工程开发者。

我们提出 Open Ontologies,一个基于 Rust 实现的开源本体工程系统,融合大模型驱动构建、形式化 OWL 推理以及通过模型上下文协议(MCP)进行本体对齐。核心发现是:稳定的一一匹配是本体对齐质量的关键因素——在 OAEI 解剖学赛道上,其 F1 达到 0.832(精确率 P = 0.963,召回率 R = 0.733),在精度上超越所有现有系统,且表现接近顶尖水平。五种权重配置的消融实验显示,当应用稳定匹配时,信号权重变化对结果影响极小(F1 波动小于 0.004),而移除该机制后 F1 降至 0.728。在会议赛道上,该方法取得 F1 = 0.438。在工具增强的本体交互中,令人意外的是:大模型仅读取原始 OWL 文件时性能为 F1 = 0.323,低于不提供任何文件时的 F1 = 0.431;而使用结构化 MCP 工具访问则达 F1 = 0.717。这表明工具结构提供了大模型无法通过解析原始语法复制的质性交互方式。系统以单个二进制文件发布,采用 MIT 许可证。

原文摘要 · Abstract (English)

We present Open Ontologies, an open-source ontology engineering system implemented in Rust that integrates LLM-driven construction with formal OWL reasoning and ontology alignment via the Model Context Protocol. Our primary finding is that stable 1-to-1 matching is the dominant factor in ontology alignment quality: on the OAEI Anatomy track, it achieves F1 = 0.832 (P = 0.963, R = 0.733), competitive with state-of-the-art systems and exceeding all in precision. Ablation across five weight configurations shows that signal weights are irrelevant when stable matching is applied (F1 varies by less than 0.004), while removing stable matching drops F1 to 0.728. On the Conference track, the same method achieves F1 = 0.438. On tool-augmented ontology interaction, we find a surprising result: an LLM reading a raw OWL file (F1 = 0.323) performs worse than the same LLM with no file at all (F1 = 0.431), while structured MCP tool access achieves F1 = 0.717. This demonstrates that tool structure provides a qualitatively different mode of access that the LLM cannot replicate by reading raw syntax. The system ships as a single binary under the MIT licence.

本体对齐大模型工具知识图谱

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。