Graph-Augmented Reasoning with Large Language Models for Tobacco Pest and Disease Management
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917243816771584 |
|---|---|
| author | Li, Siyu Song, Chenwei Zhou, Qi Zhou, Wan Liu, Xinyi |
| author_facet | Li, Siyu Song, Chenwei Zhou, Qi Zhou, Wan Liu, Xinyi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_02635 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Graph-Augmented Reasoning with Large Language Models for Tobacco Pest and Disease Management Li, Siyu Song, Chenwei Zhou, Qi Zhou, Wan Liu, Xinyi Computation and Language 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. |
| title | Graph-Augmented Reasoning with Large Language Models for Tobacco Pest and Disease Management |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.02635 |