@inproceedings{bian-etal-2026-query,
    title = "From Query to Logic: Ontology-Driven Multi-Hop Reasoning in {LLM}s",
    author = "Bian, Haonan  and
      Qi, Yutao  and
      Yang, Rui  and
      Che, Yuanxi  and
      Wang, Jiaqian  and
      Xia, Heming  and
      Zhen, Ranran",
    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.687/",
    pages = "14035--14051",
    ISBN = "979-8-89176-395-1",
    abstract = "Large Language Models (LLMs), despite their success in question answering, exhibit limitations in complex multi-hop question answering (MQA) tasks that necessitate non-linear, structured reasoning. This limitation stems from their inability to adequately capture deep conceptual relationships between entities. To overcome this challenge, we present ORACLE (Ontology-driven Reasoning And Chain for Logical Elucidation), a training-free framework that combines LLMs' generative capabilities with the structural benefits of knowledge graphs. Our approach operates through three stages: (1) dynamic construction of question-specific knowledge ontologies using LLMs, (2) transformation of these ontologies into First-Order Logic (FOL) reasoning chains, and (3) systematic decomposition of the original query into logically coherent sub-questions. Extensive experiments across a diverse set of models and standard MQA benchmarks demonstrate that our framework achieves competitive performance while producing more interpretable reasoning chains."
}