用大模型辅助构建知识图谱，提高逻辑一致性与效率
From Subsumption to Satisfiability: LLM-Assisted Active Learning for OWL Ontologies
- 将概念冲突转化为自然语言问题，由大模型判断真伪
- 实验显示在13个大模型上召回率稳定，错误仅延迟进度不引发矛盾
- 适合知识工程、自动化建模人员快速构建可靠本体
在主动学习中，成员查询允许学习者向教师提问，如“所有苹果都是水果吗？”，教师以是或否作答。这些查询可视为针对目标本体的包含关系测试。受描述逻辑中包含性归约为可满足性的启发，我们将候选公理转换为对应的反概念，并以受控自然语言形式呈现给大语言模型（LLMs）。引入大模型作为第三组件，提供逼近反概念实例的真实世界例子。该设计确保本体建模中仅可能出现Ⅱ型错误；最坏情况下，这些错误仅延迟构建过程，不会引入不一致。在13个商业大模型上的实验表明，对应于本框架中Ⅱ型错误的召回率在多个成熟本体上保持稳定。
原文摘要 · Abstract (English)
In active learning, membership queries (MQs) allow a learner to pose questions to a teacher, such as ''Is every apple a fruit?'', to which the teacher responds correctly with yes or no. These MQs can be viewed as subsumption tests with respect to the target ontology. Inspired by the standard reduction of subsumption to satisfiability in description logics, we reformulate each candidate axiom into its corresponding counter-concept and verbalise it in controlled natural language before presenting it to Large Language Models (LLMs). We introduce LLMs as a third component that provides real-world examples approximating an instance of the counter-concept. This design property ensures that only Type II errors may occur in ontology modelling; in the worst case, these errors merely delay the construction process without introducing inconsistencies. Experimental results on 13 commercial LLMs show that recall, corresponding to Type II errors in our framework, remains stable across several well-established ontologies.
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。