CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning

  • 类型:arxiv
  • 标识:2607.02262
  • 链接:http://arxiv.org/abs/2607.02262v1
  • 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:CheckRLM is a framework that improves the reliability of the reasoning process through Retrieval-Augmented Generation (RAG) by timely checking and correcting factual errors, and substantially outperforms existing baselines.
  • OpenAlex ID:W7167251588
  • OpenAlex DOI:10.48550/arxiv.2607.02262
  • DOI:10.48550/arxiv.2607.02262
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2607.02262
  • OpenAlex更新:2026-07-19
  • 待LLM分类:否
  • 标题中文:CheckRLM:基于检索增强推理的知识-思维一致性校验
  • TLDR中文:CheckRLM:通过 RAG 及时校验并修正事实错误的框架,有效提升推理过程的可靠性,大幅超越现有基线。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-04-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-07-03-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]