Saved in:
Bibliographic Details
Main Authors: Wang, Hongru, Xue, Boyang, Zhou, Baohang, Zhang, Tianhua, Wang, Cunxiang, Wang, Huimin, Chen, Guanhua, Wong, Kam-fai
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.13514
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909465995902976
author Wang, Hongru
Xue, Boyang
Zhou, Baohang
Zhang, Tianhua
Wang, Cunxiang
Wang, Huimin
Chen, Guanhua
Wong, Kam-fai
author_facet Wang, Hongru
Xue, Boyang
Zhou, Baohang
Zhang, Tianhua
Wang, Cunxiang
Wang, Huimin
Chen, Guanhua
Wong, Kam-fai
contents Previous research has typically concentrated on leveraging the internal knowledge of Large Language Models (LLMs) to answer known questions (i.e., \textit{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., \textit{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{\texttt{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{\texttt{Self-DC}} can achieve comparable or even better performance with much fewer external calls compared with several strong baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2402_13514
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions
Wang, Hongru
Xue, Boyang
Zhou, Baohang
Zhang, Tianhua
Wang, Cunxiang
Wang, Huimin
Chen, Guanhua
Wong, Kam-fai
Computation and Language
Artificial Intelligence
Previous research has typically concentrated on leveraging the internal knowledge of Large Language Models (LLMs) to answer known questions (i.e., \textit{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., \textit{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{\texttt{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{\texttt{Self-DC}} can achieve comparable or even better performance with much fewer external calls compared with several strong baselines.
title Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2402.13514