Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.01424 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908556316377088 |
|---|---|
| author | Bian, Haonan Qi, Yutao Yang, Rui Che, Yuanxi Wang, Jiaqian Xia, Heming Zhen, Ranran |
| author_facet | Bian, Haonan Qi, Yutao Yang, Rui Che, Yuanxi Wang, Jiaqian Xia, Heming Zhen, Ranran |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01424 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Query to Logic: Ontology-Driven Multi-Hop Reasoning in LLMs Bian, Haonan Qi, Yutao Yang, Rui Che, Yuanxi Wang, Jiaqian Xia, Heming Zhen, Ranran Computation and Language Artificial Intelligence 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. |
| title | From Query to Logic: Ontology-Driven Multi-Hop Reasoning in LLMs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2508.01424 |