@inproceedings{guo-etal-2025-dsrag,
title = "{DSRAG}: A Double-Stream Retrieval-Augmented Generation Framework for Countless Intent Detection",
author = "Guo, Pei and
Liu, Enjie and
Zhong, Ruichao and
Gao, Mochi and
Tan, Yunzhi and
Hu, Bo and
Li, Zang",
editor = "Chen, Weizhu and
Yang, Yi and
Kachuee, Mohammad and
Fu, Xue-Yong",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-industry.26/",
doi = "10.18653/v1/2025.naacl-industry.26",
pages = "318--328",
ISBN = "979-8-89176-194-0",
abstract = "Current intent detection work experiments with minor intent categories. However, in real-world scenarios of data analysis dialogue systems, intents are composed of combinations of numerous metrics and dimensions, resulting in countless intents and posing challenges for the language model. The retrieval-augmented generation (RAG) method efficiently retrieves key intents. However, the single retrieval route sometimes fails to recall target intents and causes incorrect results. To alleviate the above challenges, we introduce the DSRAG framework combining query-to-query (Q2Q) and query-to-metadata (Q2M) double-stream RAG approaches. Specifically, we build a repository of query statements for Q2Q using the query templates with the key intents. When a user{'}s query comes, it rapidly matches repository statements. Once the relevant query is retrieved, the results can be quickly returned. In contrast, Q2M retrieves the relevant intents from the metadata and utilizes large language models to choose the answer. Experimental results show that DSRAG achieves significant improvements compared with merely using prompt engineering and a single retrieval route."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2025-dsrag">
<titleInfo>
<title>DSRAG: A Double-Stream Retrieval-Augmented Generation Framework for Countless Intent Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pei</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enjie</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruichao</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mochi</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunzhi</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weizhu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Kachuee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xue-Yong</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-194-0</identifier>
</relatedItem>
<abstract>Current intent detection work experiments with minor intent categories. However, in real-world scenarios of data analysis dialogue systems, intents are composed of combinations of numerous metrics and dimensions, resulting in countless intents and posing challenges for the language model. The retrieval-augmented generation (RAG) method efficiently retrieves key intents. However, the single retrieval route sometimes fails to recall target intents and causes incorrect results. To alleviate the above challenges, we introduce the DSRAG framework combining query-to-query (Q2Q) and query-to-metadata (Q2M) double-stream RAG approaches. Specifically, we build a repository of query statements for Q2Q using the query templates with the key intents. When a user’s query comes, it rapidly matches repository statements. Once the relevant query is retrieved, the results can be quickly returned. In contrast, Q2M retrieves the relevant intents from the metadata and utilizes large language models to choose the answer. Experimental results show that DSRAG achieves significant improvements compared with merely using prompt engineering and a single retrieval route.</abstract>
<identifier type="citekey">guo-etal-2025-dsrag</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-industry.26</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-industry.26/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>318</start>
<end>328</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DSRAG: A Double-Stream Retrieval-Augmented Generation Framework for Countless Intent Detection
%A Guo, Pei
%A Liu, Enjie
%A Zhong, Ruichao
%A Gao, Mochi
%A Tan, Yunzhi
%A Hu, Bo
%A Li, Zang
%Y Chen, Weizhu
%Y Yang, Yi
%Y Kachuee, Mohammad
%Y Fu, Xue-Yong
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-194-0
%F guo-etal-2025-dsrag
%X Current intent detection work experiments with minor intent categories. However, in real-world scenarios of data analysis dialogue systems, intents are composed of combinations of numerous metrics and dimensions, resulting in countless intents and posing challenges for the language model. The retrieval-augmented generation (RAG) method efficiently retrieves key intents. However, the single retrieval route sometimes fails to recall target intents and causes incorrect results. To alleviate the above challenges, we introduce the DSRAG framework combining query-to-query (Q2Q) and query-to-metadata (Q2M) double-stream RAG approaches. Specifically, we build a repository of query statements for Q2Q using the query templates with the key intents. When a user’s query comes, it rapidly matches repository statements. Once the relevant query is retrieved, the results can be quickly returned. In contrast, Q2M retrieves the relevant intents from the metadata and utilizes large language models to choose the answer. Experimental results show that DSRAG achieves significant improvements compared with merely using prompt engineering and a single retrieval route.
%R 10.18653/v1/2025.naacl-industry.26
%U https://aclanthology.org/2025.naacl-industry.26/
%U https://doi.org/10.18653/v1/2025.naacl-industry.26
%P 318-328
Markdown (Informal)
[DSRAG: A Double-Stream Retrieval-Augmented Generation Framework for Countless Intent Detection](https://aclanthology.org/2025.naacl-industry.26/) (Guo et al., NAACL 2025)
ACL