Knowledge Reasoning of Large Language Models Integrating Graph-Structured Information for Pest and Disease Control in Tobacco

TL;DR

This paper introduces a novel approach combining large language models with graph-structured knowledge graphs to improve reasoning accuracy in tobacco pest and disease management, leveraging GNNs and domain-specific data.

Contribution

It presents a new framework integrating graph neural networks with LLMs for domain-specific knowledge reasoning, enhancing accuracy in complex scenarios.

Findings

Outperforms baseline methods in accuracy and reasoning depth

Effectively constructs and utilizes a domain-specific knowledge graph

Improves multi-hop and comparative reasoning capabilities

Abstract

This paper proposes a large language model (LLM) approach that integrates graph-structured information for knowledge reasoning in tobacco pest and disease control. Built upon the GraphRAG framework, the proposed method enhances knowledge retrieval and reasoning by explicitly incorporating structured information from a domain-specific knowledge graph. Specifically, LLMs are first leveraged to assist in the construction of a tobacco pest and disease knowledge graph, which organizes key entities such as diseases, symptoms, control methods, and their relationships. Based on this graph, relevant knowledge is retrieved and integrated into the reasoning process to support accurate answer generation. The Transformer architecture is adopted as the core inference model, while a graph neural network (GNN) is employed to learn expressive node representations that capture both local and global relational information within the knowledge graph. A ChatGLM-based model serves as the backbone LLM and is fine-tuned using LoRA to achieve parameter-efficient adaptation. Extensive experimental results demonstrate that the proposed approach consistently outperforms baseline methods across multiple evaluation metrics, significantly improving both the accuracy and depth of reasoning, particularly in complex multi-hop and comparative reasoning scenarios.