Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xiaoming, Wang, Ming, Yang, Xiaocui, Wang, Daling, Feng, Shi, Zhang, Yifei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914920534114304
author Zhang, Xiaoming
Wang, Ming
Yang, Xiaocui
Wang, Daling
Feng, Shi
Zhang, Yifei
author_facet Zhang, Xiaoming
Wang, Ming
Yang, Xiaocui
Wang, Daling
Feng, Shi
Zhang, Yifei
contents Multi-hop Question Answering (QA) necessitates complex reasoning by integrating multiple pieces of information to resolve intricate questions. However, existing QA systems encounter challenges such as outdated information, context window length limitations, and an accuracy-quantity trade-off. To address these issues, we propose a novel framework, the Hierarchical Retrieval-Augmented Generation Model with Rethink (HiRAG), comprising Decomposer, Definer, Retriever, Filter, and Summarizer five key modules. We introduce a new hierarchical retrieval strategy that incorporates both sparse retrieval at the document level and dense retrieval at the chunk level, effectively integrating their strengths. Additionally, we propose a single-candidate retrieval method to mitigate the limitations of multi-candidate retrieval. We also construct two new corpora, Indexed Wikicorpus and Profile Wikicorpus, to address the issues of outdated and insufficient knowledge. Our experimental results on four datasets demonstrate that HiRAG outperforms state-of-the-art models across most metrics, and our Indexed Wikicorpus is effective. The code for HiRAG is available at https://github.com/2282588541a/HiRAG
format Preprint
id arxiv_https___arxiv_org_abs_2408_11875
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering
Zhang, Xiaoming
Wang, Ming
Yang, Xiaocui
Wang, Daling
Feng, Shi
Zhang, Yifei
Computation and Language
Artificial Intelligence
Information Retrieval
Multi-hop Question Answering (QA) necessitates complex reasoning by integrating multiple pieces of information to resolve intricate questions. However, existing QA systems encounter challenges such as outdated information, context window length limitations, and an accuracy-quantity trade-off. To address these issues, we propose a novel framework, the Hierarchical Retrieval-Augmented Generation Model with Rethink (HiRAG), comprising Decomposer, Definer, Retriever, Filter, and Summarizer five key modules. We introduce a new hierarchical retrieval strategy that incorporates both sparse retrieval at the document level and dense retrieval at the chunk level, effectively integrating their strengths. Additionally, we propose a single-candidate retrieval method to mitigate the limitations of multi-candidate retrieval. We also construct two new corpora, Indexed Wikicorpus and Profile Wikicorpus, to address the issues of outdated and insufficient knowledge. Our experimental results on four datasets demonstrate that HiRAG outperforms state-of-the-art models across most metrics, and our Indexed Wikicorpus is effective. The code for HiRAG is available at https://github.com/2282588541a/HiRAG
title Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2408.11875