Optimizing RAG: Classifying Queries for Dynamic Processing

Kabir Olawore; Michael F. McTear; Yaxin Bi; David Griol

Optimizing RAG: Classifying Queries for Dynamic Processing

Kabir Olawore, Michael McTear, Yaxin Bi, David Griol

Correct Metadata for

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

In Retrieval-Augmented Generation (RAG) systems efficient information retrieval is crucial for enhancing user experience and satisfaction, as response times and computational demands significantly impact performance. RAG can be unnecessarily resource-intensive for frequently asked questions (FAQs) and simple questions. In this paper we introduce an approach in which we categorize user questions into simple queries that do not require RAG processing. Evaluation results show that our proposal reduces latency and improves response efficiency compared to systems relying solely on RAG.

Anthology ID:: 2025.iwsds-1.14
Volume:: Proceedings of the 15th International Workshop on Spoken Dialogue Systems Technology
Month:: May
Year:: 2025
Address:: Bilbao, Spain
Editors:: Maria Ines Torres, Yuki Matsuda, Zoraida Callejas, Arantza del Pozo, Luis Fernando D'Haro
Venues:: IWSDS | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 160–164
Language:
URL:: https://aclanthology.org/2025.iwsds-1.14/
DOI:
Bibkey:
Cite (ACL):: Kabir Olawore, Michael McTear, Yaxin Bi, and David Griol. 2025. Optimizing RAG: Classifying Queries for Dynamic Processing. In Proceedings of the 15th International Workshop on Spoken Dialogue Systems Technology, pages 160–164, Bilbao, Spain. Association for Computational Linguistics.
Cite (Informal):: Optimizing RAG: Classifying Queries for Dynamic Processing (Olawore et al., IWSDS 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.iwsds-1.14.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{olawore-etal-2025-optimizing,
    title = "Optimizing {RAG}: Classifying Queries for Dynamic Processing",
    author = "Olawore, Kabir  and
      McTear, Michael  and
      Bi, Yaxin  and
      Griol, David",
    editor = "Torres, Maria Ines  and
      Matsuda, Yuki  and
      Callejas, Zoraida  and
      del Pozo, Arantza  and
      D'Haro, Luis Fernando",
    booktitle = "Proceedings of the 15th International Workshop on Spoken Dialogue Systems Technology",
    month = may,
    year = "2025",
    address = "Bilbao, Spain",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.iwsds-1.14/",
    pages = "160--164",
    ISBN = "979-8-89176-248-0",
    abstract = "In Retrieval-Augmented Generation (RAG) systems efficient information retrieval is crucial for enhancing user experience and satisfaction, as response times and computational demands significantly impact performance. RAG can be unnecessarily resource-intensive for frequently asked questions (FAQs) and simple questions. In this paper we introduce an approach in which we categorize user questions into simple queries that do not require RAG processing. Evaluation results show that our proposal reduces latency and improves response efficiency compared to systems relying solely on RAG."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="olawore-etal-2025-optimizing">
    <titleInfo>
        <title>Optimizing RAG: Classifying Queries for Dynamic Processing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kabir</namePart>
        <namePart type="family">Olawore</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Michael</namePart>
        <namePart type="family">McTear</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yaxin</namePart>
        <namePart type="family">Bi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Griol</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th International Workshop on Spoken Dialogue Systems Technology</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="given">Ines</namePart>
            <namePart type="family">Torres</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yuki</namePart>
            <namePart type="family">Matsuda</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zoraida</namePart>
            <namePart type="family">Callejas</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Arantza</namePart>
            <namePart type="family">del Pozo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Luis</namePart>
            <namePart type="given">Fernando</namePart>
            <namePart type="family">D’Haro</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bilbao, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-248-0</identifier>
    </relatedItem>
    <abstract>In Retrieval-Augmented Generation (RAG) systems efficient information retrieval is crucial for enhancing user experience and satisfaction, as response times and computational demands significantly impact performance. RAG can be unnecessarily resource-intensive for frequently asked questions (FAQs) and simple questions. In this paper we introduce an approach in which we categorize user questions into simple queries that do not require RAG processing. Evaluation results show that our proposal reduces latency and improves response efficiency compared to systems relying solely on RAG.</abstract>
    <identifier type="citekey">olawore-etal-2025-optimizing</identifier>
    <location>
        <url>https://aclanthology.org/2025.iwsds-1.14/</url>
    </location>
    <part>
        <date>2025-05</date>
        <extent unit="page">
            <start>160</start>
            <end>164</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Optimizing RAG: Classifying Queries for Dynamic Processing
%A Olawore, Kabir
%A McTear, Michael
%A Bi, Yaxin
%A Griol, David
%Y Torres, Maria Ines
%Y Matsuda, Yuki
%Y Callejas, Zoraida
%Y del Pozo, Arantza
%Y D’Haro, Luis Fernando
%S Proceedings of the 15th International Workshop on Spoken Dialogue Systems Technology
%D 2025
%8 May
%I Association for Computational Linguistics
%C Bilbao, Spain
%@ 979-8-89176-248-0
%F olawore-etal-2025-optimizing
%X In Retrieval-Augmented Generation (RAG) systems efficient information retrieval is crucial for enhancing user experience and satisfaction, as response times and computational demands significantly impact performance. RAG can be unnecessarily resource-intensive for frequently asked questions (FAQs) and simple questions. In this paper we introduce an approach in which we categorize user questions into simple queries that do not require RAG processing. Evaluation results show that our proposal reduces latency and improves response efficiency compared to systems relying solely on RAG.
%U https://aclanthology.org/2025.iwsds-1.14/
%P 160-164

Download as File

Markdown (Informal)

[Optimizing RAG: Classifying Queries for Dynamic Processing](https://aclanthology.org/2025.iwsds-1.14/) (Olawore et al., IWSDS 2025)

Optimizing RAG: Classifying Queries for Dynamic Processing (Olawore et al., IWSDS 2025)

ACL

Kabir Olawore, Michael McTear, Yaxin Bi, and David Griol. 2025. Optimizing RAG: Classifying Queries for Dynamic Processing. In Proceedings of the 15th International Workshop on Spoken Dialogue Systems Technology, pages 160–164, Bilbao, Spain. Association for Computational Linguistics.