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.
@article{arxiv.2508.01424,
title = {From Query to Logic: Ontology-Driven Multi-Hop Reasoning in LLMs},
author = {Haonan Bian and Yutao Qi and Rui Yang and Yuanxi Che and Jiaqian Wang and Heming Xia and Ranran Zhen},
journal= {arXiv preprint arXiv:2508.01424},
year = {2025}
}