Self-Knowledge Retrieval Augmented Generation Framework for Patent Matching

  • 类型:arxiv
  • 标识:2608.11030
  • 链接:http://arxiv.org/abs/2608.11030v1
  • 主分类:rag
  • 形态:method
  • 被引:0
  • 被引来源:Semantic Scholar
  • S2被引:0
  • 影响力被引:0
  • TLDR:A self-knowledge RAG framework is proposed that guides LLMs to autonomously extract key technical entities and construct hierarchical ontological structures from patent matching queries, thereby enabling query expansion and precise retrieval.
  • 待LLM分类:否
  • 标题中文:面向专利匹配的自知识检索增强生成框架
  • TLDR中文:本文提出一种自我知识 RAG 框架,引导 LLM 从专利匹配查询中自主提取关键技术实体并构建层次化本体结构,从而实现查询扩展与精确检索。
  • 来源文件
  • /inbox/tom/_candidates/2026-08-12-agent-rag-longcontext-candidates.json
  • [S2 enrich]