mlsanityData to 14 Oct 2026

One Retrieval to Cover Them All: Co-occurrence-Aware Knowledge Base Reorganization for Session-Level RAG

arXiv 2606.31156 ↗First posted 30 Jun 2026cs.IR cs.AIcited by 0

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

RAG systems retrieve documents optimized for answering one query at a time. Yet enterprise users arrive with sessions, that is, coherent episodes of related questions that span semantically distant parts of the knowledge base. We show that a single retrieval call over a standard knowledge base covers only 41% of a user's session-level information need. To close this gap, we reorganize the KB offline using co-occurrence-aware clustering and expand retrieval candidates through cluster neighborhoods at query time. On WixQA (6,221 enterprise support articles), our method raises single-query session coverage to 58% (+17% absolute; 95% CI: [14.1, 20.4]), reduces retrieval calls to 70% coverage by 34%, and compresses the KB to 20% of its original size, all consistently across four embedding models and six functional domains. We argue that session-level coverage, not single-query recall, should be the primary metric for enterprise RAG evaluation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 10 of its 14 references that are in the map. First posted on arXiv 30 Jun 2026.

Builds on

10 of 14 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Cluster-based Adaptive Retrieval: Dynamic Context Selection for RAG Applications2 Oct

Other references · 9

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  5. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
  6. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  7. 2023Fine-Tuning LLaMA for Multi-Stage Text Retrievalcited by 272
  8. 2025On the Theoretical Limitations of Embedding-Based Retrievalcited by 104
  9. 2016Item2Vec: Neural Item Embedding for Collaborative Filteringcited by 72

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Training the Knowledge Base through Evidence Distillation and Write-Back Enrichment
  2. 2024RAG Does Not Work for Enterprises
  3. 2026Pre-retrieval Query Clustering for Adaptive Top-k Document Retrieval in RAG Systems
  4. 2026W-RAG: Source-Aware Retrieval for Enterprise Document Generation from Heterogeneous Knowledge Bases
  5. 2026AgenticRAG: Agentic Retrieval for Enterprise Knowledge Bases
  6. 2025Higress-RAG: A Holistic Optimization Framework for Enterprise Retrieval-Augmented Generation via Dual Hybrid Retrieval, Adaptive Routing, and CRAG
  7. 2025From Static to Dynamic: A Streaming RAG Approach to Real-time Knowledge Base
  8. 2025A Systematic Framework for Enterprise Knowledge Retrieval: Leveraging LLM-Generated Metadata to Enhance RAG Systems