English(EN) Hybrid Retrieval-Augmented Generation with Knowledge Graph Expansion, RRF Fusion, and Per-Chunk Grounded Evaluation for Enterprise Document Search

DocuSearch系统通过混合RAG和知识图谱扩展增强企业搜索

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-03 04:00

一篇新的研究论文详细介绍了DocuSearch，一个旨在提高复杂查询准确性和事实依据的企业文档搜索系统。DocuSearch集成了语义搜索（使用BGE-Large嵌入）、BM25全文搜索以及知识图谱扩展。这些检索方法通过倒数排名融合（Reciprocal Rank Fusion）进行组合，随后进行交叉编码器重排序和最大边际相关性剪枝。一项关键创新是其按块评估循环，其中一个LLM评估上下文、答案完整性和事实依据，确保只返回可靠信息。 AI

影响通过整合多种搜索技术和基于LLM的事实核查评估，该系统可以显著提高企业环境中信息检索的可靠性和准确性。

排序理由一篇关于企业文档搜索新系统的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 22 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 一篇关于企业文档搜索新系统的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Harish Saragadam, Sudhanshu Sharma, Meghana Pujari · 2026-09-03 04:00

面向企业文档搜索的混合检索增强生成，包含知识图谱扩展、RRF融合及逐块事实性评估

arXiv:2609.01617v1 Announce Type: cross Abstract: Getting accurate, grounded answers out of large enterprise document repositories is a difficult problem. Dense vector retrieval alone frequently performs poorly on queries that mix technical terminology, vendor-specific acronyms, …

本文如何被排名

报道来源 [1]

面向企业文档搜索的混合检索增强生成，包含知识图谱扩展、RRF融合及逐块事实性评估

相关实体

相关话题