EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering

  • 类型:arxiv
  • 标识:2608.21252
  • 链接:http://arxiv.org/abs/2608.21252v1
  • 主分类:rag
  • 形态:method
  • 被引:1
  • 被引来源:Semantic Scholar
  • S2被引:1
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:This work proposes EnSI-RAG (Entity-Structure-Indexed Retrieval-Augmented Generation), a framework that constructs a query-independent, entity-centered index that separates evidence localization from answer synthesis while preserving traceable source evidence.
  • OpenAlex ID:W7204107397
  • OpenAlex DOI:10.48550/arxiv.2608.21252
  • DOI:10.48550/arxiv.2608.21252
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://arxiv.org/pdf/2608.21252
  • OpenAlex更新:2026-08-31
  • 待LLM分类:否
  • 标题中文:EnSI-RAG:面向长文档问答的 Entity-Structure-Indexed RAG
  • TLDR中文:本文提出 EnSI-RAG(Entity-Structure-Indexed Retrieval-Augmented Generation),通过构建查询无关、以实体为中心的索引,将证据定位与答案合成解耦,同时保留可追溯的源证据。
  • 来源文件:
  • /inbox/tom/_candidates/2026-08-25-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]