MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jia, Pengyue, Liu, Yiding, Zhao, Xiangyu, Li, Xiaopeng, Hao, Changying, Wang, Shuaiqiang, Yin, Dawei
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917624483414016
author Jia, Pengyue
Liu, Yiding
Zhao, Xiangyu
Li, Xiaopeng
Hao, Changying
Wang, Shuaiqiang
Yin, Dawei
author_facet Jia, Pengyue
Liu, Yiding
Zhao, Xiangyu
Li, Xiaopeng
Hao, Changying
Wang, Shuaiqiang
Yin, Dawei
contents Query expansion, pivotal in search engines, enhances the representation of user information needs with additional terms. While existing methods expand queries using retrieved or generated contextual documents, each approach has notable limitations. Retrieval-based methods often fail to accurately capture search intent, particularly with brief or ambiguous queries. Generation-based methods, utilizing large language models (LLMs), generally lack corpus-specific knowledge and entail high fine-tuning costs. To address these gaps, we propose a novel zero-shot query expansion framework utilizing LLMs for mutual verification. Specifically, we first design a query-query-document generation method, leveraging LLMs' zero-shot reasoning ability to produce diverse sub-queries and corresponding documents. Then, a mutual verification process synergizes generated and retrieved documents for optimal expansion. Our proposed method is fully zero-shot, and extensive experiments on three public benchmark datasets are conducted to demonstrate its effectiveness over existing methods. Our code is available online at https://github.com/Applied-Machine-Learning-Lab/MILL to ease reproduction.
format Preprint
id arxiv_https___arxiv_org_abs_2310_19056
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion
Jia, Pengyue
Liu, Yiding
Zhao, Xiangyu
Li, Xiaopeng
Hao, Changying
Wang, Shuaiqiang
Yin, Dawei
Information Retrieval
Artificial Intelligence
Computation and Language
Query expansion, pivotal in search engines, enhances the representation of user information needs with additional terms. While existing methods expand queries using retrieved or generated contextual documents, each approach has notable limitations. Retrieval-based methods often fail to accurately capture search intent, particularly with brief or ambiguous queries. Generation-based methods, utilizing large language models (LLMs), generally lack corpus-specific knowledge and entail high fine-tuning costs. To address these gaps, we propose a novel zero-shot query expansion framework utilizing LLMs for mutual verification. Specifically, we first design a query-query-document generation method, leveraging LLMs' zero-shot reasoning ability to produce diverse sub-queries and corresponding documents. Then, a mutual verification process synergizes generated and retrieved documents for optimal expansion. Our proposed method is fully zero-shot, and extensive experiments on three public benchmark datasets are conducted to demonstrate its effectiveness over existing methods. Our code is available online at https://github.com/Applied-Machine-Learning-Lab/MILL to ease reproduction.
title MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion
topic Information Retrieval
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2310.19056