<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="varshney-mc-2026-index">
    <titleInfo>
        <title>Index-Time Prefix Injection for Multi-Tenant Retrieval: Improving Search Relevance Without Model Fine-Tuning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Vaibhav</namePart>
        <namePart type="family">Varshney</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Manjunatha</namePart>
        <namePart type="given">Naik</namePart>
        <namePart type="family">Mc</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 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yunyao</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Georg</namePart>
            <namePart type="family">Rehm</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mei</namePart>
            <namePart type="family">Tu</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, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-394-4</identifier>
    </relatedItem>
    <abstract>Multi-tenant enterprise search platforms serve hundreds of customers through a single shared retrieval model. Fine-tuning on individual customer data is typically prohibited by contractual and regulatory constraints, and maintaining per-customer models does not scale. We present index-time prefix injection, a training-free method that improves retrieval relevance by prepending domain-descriptive natural-language prefixes to documents during indexing. For example, prepending “IT service management knowledge article:” to an IT knowledge base shifts its embeddings into a tighter, more domain-coherent region of the vector space. Prefixes are discovered through a tiered strategy: LLM-based generation from document samples when data policies allow, domain-expert curation when they do not, and a standardized prefix library as fallback. Deployed across 18 languages and 400+ customer instances, the approach yields 3–8% Hit@5 improvements with zero model training. A/B tests confirm a 4.2% CTR lift. We describe the system design, evaluation at scale, and deployment lessons including failure modes.</abstract>
    <identifier type="citekey">varshney-mc-2026-index</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-industry.149/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>2231</start>
            <end>2240</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Index-Time Prefix Injection for Multi-Tenant Retrieval: Improving Search Relevance Without Model Fine-Tuning
%A Varshney, Vaibhav
%A Mc, Manjunatha Naik
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F varshney-mc-2026-index
%X Multi-tenant enterprise search platforms serve hundreds of customers through a single shared retrieval model. Fine-tuning on individual customer data is typically prohibited by contractual and regulatory constraints, and maintaining per-customer models does not scale. We present index-time prefix injection, a training-free method that improves retrieval relevance by prepending domain-descriptive natural-language prefixes to documents during indexing. For example, prepending “IT service management knowledge article:” to an IT knowledge base shifts its embeddings into a tighter, more domain-coherent region of the vector space. Prefixes are discovered through a tiered strategy: LLM-based generation from document samples when data policies allow, domain-expert curation when they do not, and a standardized prefix library as fallback. Deployed across 18 languages and 400+ customer instances, the approach yields 3–8% Hit@5 improvements with zero model training. A/B tests confirm a 4.2% CTR lift. We describe the system design, evaluation at scale, and deployment lessons including failure modes.
%U https://aclanthology.org/2026.acl-industry.149/
%P 2231-2240

Markdown (Informal)

[Index-Time Prefix Injection for Multi-Tenant Retrieval: Improving Search Relevance Without Model Fine-Tuning](https://aclanthology.org/2026.acl-industry.149/) (Varshney & Mc, ACL 2026)

• Index-Time Prefix Injection for Multi-Tenant Retrieval: Improving Search Relevance Without Model Fine-Tuning (Varshney & Mc, ACL 2026)

ACL

• Vaibhav Varshney and Manjunatha Naik Mc. 2026. Index-Time Prefix Injection for Multi-Tenant Retrieval: Improving Search Relevance Without Model Fine-Tuning. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 2231–2240, San Diego, California, USA. Association for Computational Linguistics.