@inproceedings{chen-etal-2026-smarts,
title = "{SMARTS}: A Small-to-large Model Coordinated Retrieval and Response Framework for Task-Oriented Dialogue",
author = "Chen, Jiale and
Dong, Xuelian and
Ye, Shengcheng and
Xie, Wenxiu and
Zeng, Kun and
Hao, Tianyong",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.133/",
pages = "2603--2612",
ISBN = "979-8-89176-444-6",
abstract = "Task-Oriented Dialogue (TOD) systems are commonly used to assist users in achieving specific goals through human-computer interactions. Existing methods typically employ a single model during response generation to simultaneously learn response style and perform fine-grained knowledge retrieval. However, these task-coupling methods often result in suboptimal responses generation and the inclusion of irrelevant knowledge in responses, making the optimization of TOD systems more difficult. To address this challenge, we propose a novel small-to-large model collaboration framework for task-oriented dialogue, named SMARTS. This framework utilizes a small language model to generate style-only responses (without knowledge), while a large language model retrieves top-1 relevant knowledge from the knowledge base independently. The style-only responses are finally filled with top-1 relevant knowledge and form the completed responses to users. Finally, a re-thinker is designed to check the language fluency and knowledge accuracy of responses. Experiments on two public datasets demonstrate that SMARTS outperforms existing methods by an average of 5.79{\%} in Entity F1."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-smarts">
<titleInfo>
<title>SMARTS: A Small-to-large Model Coordinated Retrieval and Response Framework for Task-Oriented Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiale</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuelian</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shengcheng</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenxiu</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyong</namePart>
<namePart type="family">Hao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Task-Oriented Dialogue (TOD) systems are commonly used to assist users in achieving specific goals through human-computer interactions. Existing methods typically employ a single model during response generation to simultaneously learn response style and perform fine-grained knowledge retrieval. However, these task-coupling methods often result in suboptimal responses generation and the inclusion of irrelevant knowledge in responses, making the optimization of TOD systems more difficult. To address this challenge, we propose a novel small-to-large model collaboration framework for task-oriented dialogue, named SMARTS. This framework utilizes a small language model to generate style-only responses (without knowledge), while a large language model retrieves top-1 relevant knowledge from the knowledge base independently. The style-only responses are finally filled with top-1 relevant knowledge and form the completed responses to users. Finally, a re-thinker is designed to check the language fluency and knowledge accuracy of responses. Experiments on two public datasets demonstrate that SMARTS outperforms existing methods by an average of 5.79% in Entity F1.</abstract>
<identifier type="citekey">chen-etal-2026-smarts</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.133/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>2603</start>
<end>2612</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SMARTS: A Small-to-large Model Coordinated Retrieval and Response Framework for Task-Oriented Dialogue
%A Chen, Jiale
%A Dong, Xuelian
%A Ye, Shengcheng
%A Xie, Wenxiu
%A Zeng, Kun
%A Hao, Tianyong
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F chen-etal-2026-smarts
%X Task-Oriented Dialogue (TOD) systems are commonly used to assist users in achieving specific goals through human-computer interactions. Existing methods typically employ a single model during response generation to simultaneously learn response style and perform fine-grained knowledge retrieval. However, these task-coupling methods often result in suboptimal responses generation and the inclusion of irrelevant knowledge in responses, making the optimization of TOD systems more difficult. To address this challenge, we propose a novel small-to-large model collaboration framework for task-oriented dialogue, named SMARTS. This framework utilizes a small language model to generate style-only responses (without knowledge), while a large language model retrieves top-1 relevant knowledge from the knowledge base independently. The style-only responses are finally filled with top-1 relevant knowledge and form the completed responses to users. Finally, a re-thinker is designed to check the language fluency and knowledge accuracy of responses. Experiments on two public datasets demonstrate that SMARTS outperforms existing methods by an average of 5.79% in Entity F1.
%U https://aclanthology.org/2026.findings-aacl.133/
%P 2603-2612
Markdown (Informal)
[SMARTS: A Small-to-large Model Coordinated Retrieval and Response Framework for Task-Oriented Dialogue](https://aclanthology.org/2026.findings-aacl.133/) (Chen et al., Findings 2026)
ACL