@inproceedings{wang-etal-2025-self,
title = "Self-{DC}: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions",
author = "Wang, Hongru and
Xue, Boyang and
Zhou, Baohang and
Zhang, Tianhua and
Wang, Cunxiang and
Wang, Huimin and
Chen, Guanhua and
Wong, Kam-Fai",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.331/",
pages = "6510--6525",
ISBN = "979-8-89176-189-6",
abstract = "Previous research has typically concentrated on leveraging the internal knowledge of Large Language Models (LLMs) to answer known questions (i.e., internal reasoning such as generate-then-read). In contrast, for questions that fall outside their known scope, these models rely on external knowledge retrieval to provide accurate responses (i.e., external acting such as retrieve-then-read). However, few previous works consider the \textit{compositional questions}, which consist of several known and unknown sub-questions, necessitating the dynamic combination of previous two methods (i.e., \textit{internal reasoning and external acting}) to achieve a better trade-off between effectiveness and efficiency. To this end, we introduce a \textbf{Self} \textbf{D}ivide-and-\textbf{C}onquer (\textit{Self-DC}) framework, accompanying with the first \textbf{C}ompositional \textbf{u}nknown \textbf{Q}uestion-\textbf{A}nswering dataset (CuQA). This framework enables LLMs to adaptively choose between using internal knowledge and retrieving external knowledge as needed, resulting in a better trade-off between effectiveness and efficiency. Experimental results on two datasets demonstrate that \textit{Self-DC} can achieve comparable or even better performance with much fewer external calls compared with several strong baselines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2025-self">
<titleInfo>
<title>Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongru</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boyang</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baohang</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianhua</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cunxiang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huimin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guanhua</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kam-Fai</namePart>
<namePart type="family">Wong</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 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</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">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Previous research has typically concentrated on leveraging the internal knowledge of Large Language Models (LLMs) to answer known questions (i.e., internal reasoning such as generate-then-read). In contrast, for questions that fall outside their known scope, these models rely on external knowledge retrieval to provide accurate responses (i.e., external acting such as retrieve-then-read). However, few previous works consider the compositional questions, which consist of several known and unknown sub-questions, necessitating the dynamic combination of previous two methods (i.e., internal reasoning and external acting) to achieve a better trade-off between effectiveness and efficiency. To this end, we introduce a Self Divide-and-Conquer (Self-DC) framework, accompanying with the first Compositional unknown Question-Answering dataset (CuQA). This framework enables LLMs to adaptively choose between using internal knowledge and retrieving external knowledge as needed, resulting in a better trade-off between effectiveness and efficiency. Experimental results on two datasets demonstrate that Self-DC can achieve comparable or even better performance with much fewer external calls compared with several strong baselines.</abstract>
<identifier type="citekey">wang-etal-2025-self</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.331/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>6510</start>
<end>6525</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions
%A Wang, Hongru
%A Xue, Boyang
%A Zhou, Baohang
%A Zhang, Tianhua
%A Wang, Cunxiang
%A Wang, Huimin
%A Chen, Guanhua
%A Wong, Kam-Fai
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F wang-etal-2025-self
%X Previous research has typically concentrated on leveraging the internal knowledge of Large Language Models (LLMs) to answer known questions (i.e., internal reasoning such as generate-then-read). In contrast, for questions that fall outside their known scope, these models rely on external knowledge retrieval to provide accurate responses (i.e., external acting such as retrieve-then-read). However, few previous works consider the compositional questions, which consist of several known and unknown sub-questions, necessitating the dynamic combination of previous two methods (i.e., internal reasoning and external acting) to achieve a better trade-off between effectiveness and efficiency. To this end, we introduce a Self Divide-and-Conquer (Self-DC) framework, accompanying with the first Compositional unknown Question-Answering dataset (CuQA). This framework enables LLMs to adaptively choose between using internal knowledge and retrieving external knowledge as needed, resulting in a better trade-off between effectiveness and efficiency. Experimental results on two datasets demonstrate that Self-DC can achieve comparable or even better performance with much fewer external calls compared with several strong baselines.
%U https://aclanthology.org/2025.naacl-long.331/
%P 6510-6525
Markdown (Informal)
[Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions](https://aclanthology.org/2025.naacl-long.331/) (Wang et al., NAACL 2025)
ACL
- Hongru Wang, Boyang Xue, Baohang Zhou, Tianhua Zhang, Cunxiang Wang, Huimin Wang, Guanhua Chen, and Kam-Fai Wong. 2025. Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 6510–6525, Albuquerque, New Mexico. Association for Computational Linguistics.