{"ID":2887661,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.01424","arxiv_id":"2508.01424","title":"From Query to Logic: Ontology-Driven Multi-Hop Reasoning in LLMs","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** (**O**ntology-driven **R**easoning **A**nd **C**hain for **L**ogical **E**ucidation), 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 reasoning chains, and (3) systematic decomposition of the original query into logically coherent sub-questions. Experimental results on several standard MQA benchmarks show that our framework achieves highly competitive performance, rivaling current state-of-the-art models like DeepSeek-R1. Detailed analyses further confirm the effectiveness of each component, while demonstrating that our method generates more logical and interpretable reasoning chains than existing approaches.","short_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 overco...","url_abs":"https://arxiv.org/abs/2508.01424","url_pdf":"https://arxiv.org/pdf/2508.01424v2","authors":"[\"Haonan Bian\",\"Yutao Qi\",\"Rui Yang\",\"Yuanxi Che\",\"Jiaqian Wang\",\"Heming Xia\",\"Ranran Zhen\"]","published":"2025-08-02T16:12:42Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}