@inproceedings{yuqing-etal-2026-search,
    title = "{SEARCH}-{R}: Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator for Multi-hop Question Answering",
    author = "Yuqing, FU  and
      Deng, Yimin  and
      Wang, Wanyu  and
      Wang, Yuhao  and
      Wang, Yejing  and
      Liu, Hongshi  and
      Wang, Yiqi  and
      Han, Xiao  and
      Wang, Maolin  and
      Zhao, Guoshuai  and
      Chang, Yi  and
      Zhao, Xiangyu",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1953/",
    pages = "39183--39196",
    ISBN = "979-8-89176-395-1",
    abstract = "Multi-hop Question Answering (MHQA) aims to answer questions that require multi-step reasoning. The complexity of user queries, coupled with potential knowledge deficiencies in Large Language Models (LLMs), gives rise to two pivotal challenges that underpin the performance on this task: the correct identification of the reasoning path and the accurate retrieval of essential knowledge.{~}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."
}