CAMAGRI-GPT:A parameter-efficient agricultural knowledge system using domain-adapted large language models with retrieval augmentationOA
Despite their transformative potential,large language models(LLMs)remain underutilized in agriculture due to domain-specific data scarcity and computational constraints.This study presents CAMAGRI-GPT,a parameter-efficient agricultural consultation system that addresses these critical challenges through innovative domain adaptation.A corpus of 2.3 million annotated entries was constructed from raw documents(κ=0.82 agreement,18 categories)and employed LoRA(r=8)and P-tuning v2 to reduce trainable parameters to 0.2%while maintaining 95.8%performance.The RAG framework with HNSW indexing achieves(87±12)ms retrieval latency,enabling real-time consultation.CAMAGRI-GPT demonstrated over 90.0%accuracy across three representative agricultural tasks(crop management,pest and disease diagnosis,and agricultural Q&A),consistently outperforming GPT-3 and BERT-Agri baselines,p<0.001.Median response latency remained below 2 s across all query categories,meeting field deployment requirements.These results demonstrate that domain-adapted LLMs can effectively deliver expert-level agricultural knowledge to resource-constrained farming communities,offering scalable and sustainable solutions to complement declining traditional extension services.
Qianchuan Li;Xin Dai;Feng Yu;Junsheng Dai;Shengwei Wang;Rupeng Luan;Xiaowei Wang;Xiaojing Qin;Shiwei Xu
Institute of Data Science and Agricultural Economics,Beijing Academy of Agriculture and Forestry Sciences,Beijing 100097,China Key Laboratory of Intelligent Seedling Technology Innovation,Ministry of Agriculture and Rural Affairs,Beijing 100097,ChinaAgricultural Information Institute,Chinese Academy of Agricultural Sciences,Beijing 100081,ChinaInstitute of Data Science and Agricultural Economics,Beijing Academy of Agriculture and Forestry Sciences,Beijing 100097,China Key Laboratory of Intelligent Seedling Technology Innovation,Ministry of Agriculture and Rural Affairs,Beijing 100097,ChinaXinjiang Academy of Agricultural Sciences,Urumqi 830091,ChinaAgricultural Information Institute,Chinese Academy of Agricultural Sciences,Beijing 100081,ChinaInstitute of Data Science and Agricultural Economics,Beijing Academy of Agriculture and Forestry Sciences,Beijing 100097,China Key Laboratory of Intelligent Seedling Technology Innovation,Ministry of Agriculture and Rural Affairs,Beijing 100097,ChinaInstitute of Agricultural Information,Xinjiang Academy of Agricultural Sciences,Urumqi 830091,ChinaInstitute of Data Science and Agricultural Economics,Beijing Academy of Agriculture and Forestry Sciences,Beijing 100097,China Key Laboratory of Intelligent Seedling Technology Innovation,Ministry of Agriculture and Rural Affairs,Beijing 100097,ChinaAgricultural Information Institute,Chinese Academy of Agricultural Sciences,Beijing 100081,China Key Laboratory of Agricultural Monitoring and Early Warning,Ministry of Agriculture and Rural Affairs,Beijing 100081,China
农业科技
agricultural large language modelCAMAGRI-GPTdomain adaptationretrieval-augmented generationknowledge disseminationparameter-efficient fine-tuning
《International Journal of Agricultural and Biological Engineering》 2026 (2)
P.245-261,17
supported by the National Key Research and Development Program of China(Grant No.2023YFD2000105)the Beijing Academy of Agriculture and Forestry Sciences Reform and Development Program“Research and Application of Agricultural Data Science Technology”(Grant No.GGFZSJS2026)。
评论