用知识图谱增强大模型，让烟草病虫害管理更准确可靠。
Graph-Augmented Reasoning with Large Language Models for Tobacco Pest and Disease Management
- 构建烟草领域知识图谱，通过实体关联提供推理依据。
- 多跳推理任务准确率提升显著，最高达18.3%。
- 适合农业专家和智能诊断系统开发者使用。
本文提出一种基于图增强推理的烟草病虫害管理框架，将结构化领域知识融入大语言模型。在GraphRAG基础上，构建领域专用知识图谱，并检索与查询相关的子图作为生成过程中的关系证据。采用ChatGLM作为Transformer主干网络，结合LoRA实现参数高效微调，并利用图神经网络学习节点表示，捕捉症状-疾病-防治措施之间的依赖关系。通过显式建模疾病、症状、农药及防控措施为相互关联的实体，系统支持超越表面文本相似性的证据感知检索。检索到的图谱证据被引入大模型输入，引导生成符合领域逻辑的建议，缓解幻觉或不当治疗问题。实验结果表明，该框架在各类基准上均优于仅依赖文本的基线模型，尤其在需要多跳推理和比较判断的任务中表现突出，最大提升达18.3%。
原文摘要 · Abstract (English)
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.
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。