SymbolLKG: Towards Verifiable Logical Reasoning via Logical Knowledge Graph and Symbolic Solvers

• 类型：arxiv
• 标识：2608.26836
• 链接：http://arxiv.org/abs/2608.26836v1
• 主分类：rag
• 形态：method
• TLDR：Large Language Models (LLMs) have demonstrated remarkable proficiency in natural language understanding, yet they struggle with strict multi-step reasoning, frequently suffering from hallucinations and inconsistency. Existing solutions like Chain-of-Thought (CoT) lack rigorous verification mechanisms, while standard Retrieval-Augmented Generation (RAG) often misses the complex, structural dependencies inherent in logical tasks. To bridge this gap, we propose a Neuro-Symbolic architecture that integrates a Logical Knowledge Graph (LKG) with dynamic solver routing. Specifically, we introduce an
• 待LLM分类：否
• 标题中文：SymbolLKG：通过逻辑知识图谱与符号求解器实现可验证的逻辑推理
• TLDR中文：大语言模型 (LLM) 在自然语言理解上表现突出，但在严格多步推理上仍力不从心，常出现幻觉与不一致。现有方案如思维链 (CoT) 缺乏严格验证机制，而标准检索增强生成 (RAG) 常遗漏逻辑任务中固有的复杂结构依赖。为弥合这一差距，我们提出一种神经-符号架构，将逻辑知识图谱 (LKG) 与动态求解器路由相结合。具体地，我们引入一种
• 来源文件：
• /inbox/tom/_candidates/2026-09-01-rag-retrieval-reranking-candidates.json