用知识图谱增强大模型逻辑推理，让复杂问题拆解更清晰
From Query to Logic: Ontology-Driven Multi-Hop Reasoning in LLMs
- 基于问题动态构建知识本体，将语义关系结构化
- 生成可验证的逻辑推理链，在多个基准上表现媲美顶尖模型
- 无需训练即可提升推理可解释性，适合需要可信推理的场景
大语言模型在问答任务中虽已取得成功，但在需非线性、结构性推理的多跳问答（MQA）任务中仍存在局限，主要源于对实体间深层概念关系捕捉不足。为此，我们提出**ORACLE**（Ontology-driven Reasoning and Chain for Logical Elucidation），一种无需训练的框架，融合大模型生成能力与知识图谱的结构优势。该方法分三阶段进行：(1) 利用大模型动态构建与问题相关的知识本体；(2) 将本体转化为一阶逻辑推理链；(3) 系统分解原问题为逻辑连贯的子问题。在多个标准MQA基准上的实验表明，该框架性能优异，可媲美现有顶尖模型如DeepSeek-R1。详细分析证实各组件有效性，且相比现有方法生成的推理链更具逻辑性与可解释性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。