Search papers, labs, and topics across Lattice.
This paper introduces a Neuro-Symbolic architecture that combines a Logical Knowledge Graph (LKG) with dynamic solver routing to enhance the logical reasoning capabilities of Large Language Models (LLMs). By treating logical rules and constraints as topological nodes within an ontology-based LKG, the framework effectively models complex dependencies and improves task dispatching to optimal symbolic engines. Experimental results show that this approach significantly outperforms existing methods, achieving higher accuracy and providing verifiable reasoning paths on logical reasoning benchmarks.
Verifiable logical reasoning in LLMs can be achieved by integrating a Logical Knowledge Graph with dynamic solver routing, outperforming traditional methods.
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 ontology-based LKG that treats logical rules and constraints as first-class topological nodes, enabling explicit modeling of dependencies extracted from text. We further design a Logic Router to dynamically dispatch tasks to the optimal symbolic engine, which is supported by a topology-aware hybrid retrieval mechanism. Experimental results on logical reasoning benchmarks demonstrate that our framework significantly outperforms state-of-the-art prompting and RAG baselines, delivering higher accuracy and verifiable reasoning paths.
