TreeHop: Generate and Filter Next Query Embeddings Efficiently for Multi-hop Question Answering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Zhonghao, Zhang, Kunpeng, Ou, Jinghuai, Liu, Shuliang, Hu, Xuming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915266676391936
author Li, Zhonghao
Zhang, Kunpeng
Ou, Jinghuai
Liu, Shuliang
Hu, Xuming
author_facet Li, Zhonghao
Zhang, Kunpeng
Ou, Jinghuai
Liu, Shuliang
Hu, Xuming
contents Retrieval-augmented generation (RAG) systems face significant challenges in multi-hop question answering (MHQA), where complex queries require synthesizing information across multiple document chunks. Existing approaches typically rely on iterative LLM-based query rewriting and routing, resulting in high computational costs due to repeated LLM invocations and multi-stage processes. To address these limitations, we propose TreeHop, an embedding-level framework without the need for LLMs in query refinement. TreeHop dynamically updates query embeddings by fusing semantic information from prior queries and retrieved documents, enabling iterative retrieval through embedding-space operations alone. This method replaces the traditional "Retrieve-Rewrite-Vectorize-Retrieve" cycle with a streamlined "Retrieve-Embed-Retrieve" loop, significantly reducing computational overhead. Moreover, a rule-based stop criterion is introduced to further prune redundant retrievals, balancing efficiency and recall rate. Experimental results show that TreeHop rivals advanced RAG methods across three open-domain MHQA datasets, achieving comparable performance with only 5\%-0.4\% of the model parameter size and reducing the query latency by approximately 99\% compared to concurrent approaches. This makes TreeHop a faster and more cost-effective solution for deployment in a range of knowledge-intensive applications. For reproducibility purposes, codes and data are available here: https://github.com/allen-li1231/TreeHop-RAG.
format Preprint
id arxiv_https___arxiv_org_abs_2504_20114
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TreeHop: Generate and Filter Next Query Embeddings Efficiently for Multi-hop Question Answering
Li, Zhonghao
Zhang, Kunpeng
Ou, Jinghuai
Liu, Shuliang
Hu, Xuming
Information Retrieval
Artificial Intelligence
Human-Computer Interaction
Machine Learning
Retrieval-augmented generation (RAG) systems face significant challenges in multi-hop question answering (MHQA), where complex queries require synthesizing information across multiple document chunks. Existing approaches typically rely on iterative LLM-based query rewriting and routing, resulting in high computational costs due to repeated LLM invocations and multi-stage processes. To address these limitations, we propose TreeHop, an embedding-level framework without the need for LLMs in query refinement. TreeHop dynamically updates query embeddings by fusing semantic information from prior queries and retrieved documents, enabling iterative retrieval through embedding-space operations alone. This method replaces the traditional "Retrieve-Rewrite-Vectorize-Retrieve" cycle with a streamlined "Retrieve-Embed-Retrieve" loop, significantly reducing computational overhead. Moreover, a rule-based stop criterion is introduced to further prune redundant retrievals, balancing efficiency and recall rate. Experimental results show that TreeHop rivals advanced RAG methods across three open-domain MHQA datasets, achieving comparable performance with only 5\%-0.4\% of the model parameter size and reducing the query latency by approximately 99\% compared to concurrent approaches. This makes TreeHop a faster and more cost-effective solution for deployment in a range of knowledge-intensive applications. For reproducibility purposes, codes and data are available here: https://github.com/allen-li1231/TreeHop-RAG.
title TreeHop: Generate and Filter Next Query Embeddings Efficiently for Multi-hop Question Answering
topic Information Retrieval
Artificial Intelligence
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2504.20114