Abstract
Large language models (LLMs) offer new opportunities for constructing knowledge graphs (KGs) from unstructured clinical narratives. However, existing approaches often rely on structured inputs and lack robust validation of factual accuracy and semantic consistency, limitations that are especially problematic in oncology. We introduce an end-to-end framework for clinical KG construction and evaluation directly from free text using multi-agent prompting and a schema-constrained Retrieval-Augmented Generation (KG-RAG) strategy. Our pipeline integrates (1) prompt-driven entity, attribute, and relation extraction; (2) entropy-based uncertainty scoring; (3) ontology-aligned RDF/OWL schema generation; and (4) multi-LLM consensus validation for hallucination detection and semantic refinement. Beyond static graph construction, the framework supports continuous refinement and self-supervised evaluation, enabling iterative improvement of graph quality. Applied to two oncology cohorts (PDAC and BRCA), our method produces interpretable, SPARQL-compatible, and clinically grounded knowledge graphs without relying on gold-standard annotations. Experimental results demonstrate consistent gains in precision, relevance, and ontology compliance over baseline methods.
Abstract (translated)
大型语言模型（LLM）为从非结构化临床叙述中构建知识图谱（KG）提供了新的机会。然而，现有的方法通常依赖于结构化的输入，并且缺乏对事实准确性和语义一致性进行稳健验证的能力，在肿瘤学领域尤其成问题。我们引入了一种端到端框架，该框架可以直接从自由文本使用多代理提示和约束模式的检索增强生成（KG-RAG）策略构建并评估临床知识图谱。我们的流水线整合了以下四个关键步骤：(1) 提示驱动下的实体、属性和关系抽取；(2) 基于熵的不确定性评分；(3) 与本体一致的RDF/OWL模式生成；以及 (4) 多LLM共识验证以检测幻觉并进行语义细化。除了静态图谱构建外，该框架还支持持续改进和自我监督评估，从而能够不断优化图的质量。在两个肿瘤学队列（胰腺导管腺癌PDAC 和 BRCA）的应用中，我们的方法无需依赖金标准注释，即可生成可解释、SPARQL兼容且具有临床依据的知识图谱。实验结果表明，在精确度、相关性和符合本体规范方面，相较于基线方法，该方法始终表现出显著的优势。
URL
https://arxiv.org/abs/2601.01844
