Robust Interpretation of Historical Documents in Knowledge Graphs Through Query Inference and Execution

  • 类型:arxiv
  • 标识:2607.24475
  • 链接:http://arxiv.org/abs/2607.24475v1
  • 主分类:llm-infra
  • 形态:method
  • 被引:0
  • 被引来源:Semantic Scholar
  • S2被引:0
  • 影响力被引:0
  • TLDR:This paper introduces a semi-symbolic framework that integrates word-spotting techniques for post-OCR correction with a knowledge graph representation that enables the agent to access information through synthesized queries that are robust to misinterpretation and hallucination.
  • 待LLM分类:否
  • 标题中文:通过查询推断与执行实现知识图谱中历史文档的鲁棒解读
  • TLDR中文:本文提出一个半符号化框架,将用于 OCR 后校正的 word-spotting 技术与知识图谱表示相结合,使 agent 可通过合成查询访问信息,从而对误读和幻觉具有鲁棒性。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-28-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-07-29-agent-rag-longcontext-candidates.json
  • [S2 enrich]