@inproceedings{ratnakar-etal-2026-one,
title = "One Retrieval to Cover Them All: Co-occurrence-Aware Knowledge Base Reorganization for Session-Level {RAG}",
author = "Ratnakar, Shivam and
Zhu, Yixuan and
Cheng, Cecilia and
Vijayakumar, Chaya",
editor = "Chen, Canyu and
Zhang, Yuji and
Li, Zoey Sha and
Wang, Zihan and
Wang, Qineng and
Su, Jinyan and
Kargupta, Priyanka and
Marjanovi{\'c}, Sara Vera and
Pan, Jeff Z. and
Bansal, Mohit and
Augenstein, Isabelle and
Han, Jiawei and
Ji, Heng and
Li, Manling",
booktitle = "Proceedings of the 4th Workshop on Towards Knowledgeable Foundation Models ({K}now{FM} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.knowfm-1.14/",
pages = "173--182",
ISBN = "979-8-89176-403-3",
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 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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ratnakar-etal-2026-one">
<titleInfo>
<title>One Retrieval to Cover Them All: Co-occurrence-Aware Knowledge Base Reorganization for Session-Level RAG</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shivam</namePart>
<namePart type="family">Ratnakar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixuan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cecilia</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaya</namePart>
<namePart type="family">Vijayakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Towards Knowledgeable Foundation Models (KnowFM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Canyu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zoey</namePart>
<namePart type="given">Sha</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zihan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qineng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinyan</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priyanka</namePart>
<namePart type="family">Kargupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="given">Vera</namePart>
<namePart type="family">Marjanović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeff</namePart>
<namePart type="given">Z</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manling</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-403-3</identifier>
</relatedItem>
<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 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.</abstract>
<identifier type="citekey">ratnakar-etal-2026-one</identifier>
<location>
<url>https://aclanthology.org/2026.knowfm-1.14/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>173</start>
<end>182</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T One Retrieval to Cover Them All: Co-occurrence-Aware Knowledge Base Reorganization for Session-Level RAG
%A Ratnakar, Shivam
%A Zhu, Yixuan
%A Cheng, Cecilia
%A Vijayakumar, Chaya
%Y Chen, Canyu
%Y Zhang, Yuji
%Y Li, Zoey Sha
%Y Wang, Zihan
%Y Wang, Qineng
%Y Su, Jinyan
%Y Kargupta, Priyanka
%Y Marjanović, Sara Vera
%Y Pan, Jeff Z.
%Y Bansal, Mohit
%Y Augenstein, Isabelle
%Y Han, Jiawei
%Y Ji, Heng
%Y Li, Manling
%S Proceedings of the 4th Workshop on Towards Knowledgeable Foundation Models (KnowFM 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-403-3
%F ratnakar-etal-2026-one
%X 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.
%U https://aclanthology.org/2026.knowfm-1.14/
%P 173-182
Markdown (Informal)
[One Retrieval to Cover Them All: Co-occurrence-Aware Knowledge Base Reorganization for Session-Level RAG](https://aclanthology.org/2026.knowfm-1.14/) (Ratnakar et al., KnowFM 2026)
ACL