One Retrieval to Cover Them All: Co-occurrence-Aware Knowledge Base Reorganization for Session-Level RAG
Year: 2026
Type: conference-paper
Abstract: 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 singlequery 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.
Institution: University of Southern California
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166823779