Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ye, Linhao, Yu, Lang, Lei, Zhikai, Chen, Qin, Zhou, Jie, He, Liang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908387972743168
author Ye, Linhao
Yu, Lang
Lei, Zhikai
Chen, Qin
Zhou, Jie
He, Liang
author_facet Ye, Linhao
Yu, Lang
Lei, Zhikai
Chen, Qin
Zhou, Jie
He, Liang
contents Retrieval-augmented generation (RAG) is usually integrated into large language models (LLMs) to mitigate hallucinations and knowledge obsolescence. Whereas,conventional one-step retrieve-and-read methods are insufficient for multi-hop question answering, facing challenges of retrieval semantic mismatching and the high cost in handling interdependent subquestions. In this paper, we propose Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering (Q-DREAM). Q-DREAM consists of three key modules: (1) the Question Decomposition Module (QDM), which decomposes multi-hop questions into fine-grained subquestions; (2) the Subquestion Dependency Optimizer Module (SDOM), which models the interdependent relations of subquestions for better understanding; and (3) the Dynamic Passage Retrieval Module (DPRM), which aligns subquestions with relevant passages by optimizing the semantic embeddings. Experimental results across various benchmarks demonstrate that Q-DREAM significantly outperforms existing RAG methods, achieving state-of-the-art performance in both in-domain and out-of-domain settings. Notably, Q-DREAM also improves retrieval efficiency while maintaining high accuracy compared with recent baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00491
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering
Ye, Linhao
Yu, Lang
Lei, Zhikai
Chen, Qin
Zhou, Jie
He, Liang
Information Retrieval
Retrieval-augmented generation (RAG) is usually integrated into large language models (LLMs) to mitigate hallucinations and knowledge obsolescence. Whereas,conventional one-step retrieve-and-read methods are insufficient for multi-hop question answering, facing challenges of retrieval semantic mismatching and the high cost in handling interdependent subquestions. In this paper, we propose Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering (Q-DREAM). Q-DREAM consists of three key modules: (1) the Question Decomposition Module (QDM), which decomposes multi-hop questions into fine-grained subquestions; (2) the Subquestion Dependency Optimizer Module (SDOM), which models the interdependent relations of subquestions for better understanding; and (3) the Dynamic Passage Retrieval Module (DPRM), which aligns subquestions with relevant passages by optimizing the semantic embeddings. Experimental results across various benchmarks demonstrate that Q-DREAM significantly outperforms existing RAG methods, achieving state-of-the-art performance in both in-domain and out-of-domain settings. Notably, Q-DREAM also improves retrieval efficiency while maintaining high accuracy compared with recent baselines.
title Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering
topic Information Retrieval
url https://arxiv.org/abs/2506.00491