Detecting Knowledge Inconsistencies Across Text, Tables, and Knowledge Graphs

  • 类型:arxiv
  • 标识:2607.25959
  • 链接:http://arxiv.org/abs/2607.25959v1
  • 主分类:rag
  • 形态:method
  • 被引:0
  • 被引来源:Semantic Scholar + OpenAlex
  • S2被引:0
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:Kontrast is presented, an automatic framework that uses Text-to-SPARQL and LLM reasoning to compare table-based answers with KG evidence and categorize the resulting inconsistencies, and shows that text, tables, and KGs can complement and correct one another through systematic comparison.
  • OpenAlex ID:W7171632910
  • OpenAlex DOI:10.48550/arxiv.2607.25959
  • DOI:10.48550/arxiv.2607.25959
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2607.25959
  • OpenAlex更新:2026-08-25
  • 待LLM分类:否
  • 标题中文:跨文本、表格与知识图谱的知识不一致检测
  • TLDR中文:本文提出 Kontrast,一种利用 Text-to-SPARQL 与 LLM 推理将基于表格的答案与 KG 证据进行对比并对所产生的不一致性进行分类的自动框架,并表明文本、表格与 KG 可通过系统性对比相互补充与纠错。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-29-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-07-30-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]