Graph-Augmented Reasoning with Large Language Models for Tobacco Pest and Disease Management
This work addresses domain-specific challenges in agricultural AI by providing more accurate and evidence-based recommendations for tobacco pest and disease management, though it is incremental as it builds on existing GraphRAG methods.
This paper tackled the problem of improving large language models for tobacco pest and disease management by integrating structured domain knowledge via a graph-augmented reasoning framework, resulting in consistent improvements over text-only baselines, with the largest gains on multi-hop and comparative reasoning questions.
This paper proposes a graph-augmented reasoning framework for tobacco pest and disease management that integrates structured domain knowledge into large language models. Building on GraphRAG, we construct a domain-specific knowledge graph and retrieve query-relevant subgraphs to provide relational evidence during answer generation. The framework adopts ChatGLM as the Transformer backbone with LoRA-based parameter-efficient fine-tuning, and employs a graph neural network to learn node representations that capture symptom-disease-treatment dependencies. By explicitly modeling diseases, symptoms, pesticides, and control measures as linked entities, the system supports evidence-aware retrieval beyond surface-level text similarity. Retrieved graph evidence is incorporated into the LLM input to guide generation toward domain-consistent recommendations and to mitigate hallucinated or inappropriate treatments. Experimental results show consistent improvements over text-only baselines, with the largest gains observed on multi-hop and comparative reasoning questions that require chaining multiple relations.