SEARCH-R: Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator for Multi-hop Question Answering

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Fu, Yuqing, Deng, Yimin, Wang, Wanyu, Wang, Yuhao, Wang, Yejing, Liu, Hongshi, Wang, Yiqi, Han, Xiao, Wang, Maolin, Zhao, Guoshuai, Chang, Yi, Zhao, Xiangyu
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917440050429952
author Fu, Yuqing
Deng, Yimin
Wang, Wanyu
Wang, Yuhao
Wang, Yejing
Liu, Hongshi
Wang, Yiqi
Han, Xiao
Wang, Maolin
Zhao, Guoshuai
Chang, Yi
Zhao, Xiangyu
author_facet Fu, Yuqing
Deng, Yimin
Wang, Wanyu
Wang, Yuhao
Wang, Yejing
Liu, Hongshi
Wang, Yiqi
Han, Xiao
Wang, Maolin
Zhao, Guoshuai
Chang, Yi
Zhao, Xiangyu
contents Multi-hop Question Answering (MHQA) aims to answer questions that require multi-step reasoning. It presents two key challenges: generating correct reasoning paths in response to the complex user queries, and accurately retrieving essential knowledge in the face of potential limitations in large language models (LLMs). Existing approaches primarily rely on prompt-based methods to generate reasoning paths, which are further combined with traditional sparse or dense retrieval to produce the final answer. However, the generation of reasoning paths commonly lacks effective control over the generative process, thus leading the reasoning astray. Meanwhile, the retrieval methods over-rely on knowledge matching or similarity scores rather than evaluating the practical utility of the information, resulting in retrieving homogeneous or non-useful information. Therefore, we propose a Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator framework named SEARCH-R. Specifically, SEARCH-R trains an end-to-end reasoning path navigator, which is able to provide a powerful sub-question decomposer by fine-tuning the Llama3.1-8B model. Moreover, a novel dependency tree-based retrieval is designed to evaluate the informational contribution of the document quantitatively. Extensive experiments on three challenging multi-hop datasets validate the effectiveness of the proposed framework. The code and dataset are available at: https://github.com/Applied-Machine-Learning-Lab/ACL2026_SEARCH-R.
format Preprint
id arxiv_https___arxiv_org_abs_2604_24515
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SEARCH-R: Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator for Multi-hop Question Answering
Fu, Yuqing
Deng, Yimin
Wang, Wanyu
Wang, Yuhao
Wang, Yejing
Liu, Hongshi
Wang, Yiqi
Han, Xiao
Wang, Maolin
Zhao, Guoshuai
Chang, Yi
Zhao, Xiangyu
Computation and Language
Multi-hop Question Answering (MHQA) aims to answer questions that require multi-step reasoning. It presents two key challenges: generating correct reasoning paths in response to the complex user queries, and accurately retrieving essential knowledge in the face of potential limitations in large language models (LLMs). Existing approaches primarily rely on prompt-based methods to generate reasoning paths, which are further combined with traditional sparse or dense retrieval to produce the final answer. However, the generation of reasoning paths commonly lacks effective control over the generative process, thus leading the reasoning astray. Meanwhile, the retrieval methods over-rely on knowledge matching or similarity scores rather than evaluating the practical utility of the information, resulting in retrieving homogeneous or non-useful information. Therefore, we propose a Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator framework named SEARCH-R. Specifically, SEARCH-R trains an end-to-end reasoning path navigator, which is able to provide a powerful sub-question decomposer by fine-tuning the Llama3.1-8B model. Moreover, a novel dependency tree-based retrieval is designed to evaluate the informational contribution of the document quantitatively. Extensive experiments on three challenging multi-hop datasets validate the effectiveness of the proposed framework. The code and dataset are available at: https://github.com/Applied-Machine-Learning-Lab/ACL2026_SEARCH-R.
title SEARCH-R: Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator for Multi-hop Question Answering
topic Computation and Language
url https://arxiv.org/abs/2604.24515