面向结构化知识检索与推理的可信领域AI架构
原标题：Trustworthy Domain-Specific AI for Structured Knowledge Retrieval and Reasoning
AI 摘要
马里兰大学巴尔的摩县分校的 Ryan C. Barron 在博士论文中提出了一套面向特定领域、可部署的模块化架构，用于将大量非结构化领域文本转化为可检索、可推理的结构化知识。论文提出 Binary Bleed 二分搜索方法和 HNMFk 深度自适应主题建模，并将结果同时实例化为类型化知识图谱与语义对齐的向量存储。研究还提出 Tensor-Structured RAG（T-SRAG）和基于张量的链接预测推理，在网络安全、法律、材料科学和医疗领域验证了检索精度提升与幻觉缓解。
正文节选
Self-Organizing Adaptive Knowledge Evolution and Discovery: A Dense Domain-Specific Multi-Agent, Multi-Context Knowledge Graph Framework for Transferable and Traceable Knowledge ABSTRACT This dissertation presents a production-ready architecture that addresses the challenge of transforming vast volumes of unstructured, domain-specific text into structured and actionable knowledge representations that enable both retrieval and reasoning. Traditional pipelines for knowledge discovery remain fragme