数字农科院2.0

Extracting Fruit Disease Knowledge from Research Papers Based on Large Language Models and Prompt Engineering

文献类型： 外文期刊

作者： Yunqiao Fei;Jingchao Fan;Guomin Zhou

作者机构：

关键词： fruit tree diseases;knowledge extraction;large language models;prompt engineering;research papers

期刊名称： Applied Sciences (Switzerland)

ISSN： 2076-3417

年卷期： 2025 年 15 卷 2 期

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： In China, fruit tree diseases are a significant threat to the development of the fruit tree industry, and knowledge about fruit tree diseases is the most needed professional knowledge for fruit farmers and other practitioners in the fruit tree industry. Research papers are the primary sources of professional knowledge that represent the cutting-edge progress in fruit disease research. Traditional knowledge engineering methods for knowledge acquisition require extensive and cumbersome preparatory work, and they demand a high level of professional background and information technology skills from the handlers. This paper, from the perspective of fruit tree industry knowledge dissemination, aims at users such as fruit farmers, fruit tree experts, fruit tree knowledge communicators, and information gatherers. It proposes a fast, cost-effective, and low-technical-barrier method for extracting fruit tree disease knowledge from research paper abstracts—K-Extract, based on large language models (LLMs) and prompt engineering. Under zero-shot conditions, K-Extract utilizes conversational LLMs to automate the extraction of fruit tree disease knowledge. The K-Extract method has constructed a comprehensive classification system for fruit tree diseases and, through a series of optimized prompt questions, effectively overcomes the deficiencies of LLM models in providing factual accuracy. This paper tests multiple LLM models available in the Chinese market, and the results show that K-Extract can seamlessly integrate with any conversational LLM model, with the DeepSeek model and the Kimi model performing particularly well. The experimental results indicate that LLM models have a high accuracy rate in handling judgment tasks and simple knowledge Q&A tasks. The K-Extract method is simple, efficient, and accurate, and can serve as a convenient tool for knowledge extraction in the agricultural field.

分类号：

  • 相关文献

[1]Automated Knowledge Extraction in the Field of Wheat Sharp Eyespot Control. Keyi Liu,Yunpeng Cui. 2024

[2]Progress and opportunities of foundation models in bioinformatics. Qing Li,Zhihang Hu,Yixuan Wang,Lei Li,Yimin Fan,Irwin King,Gengjie Jia,Sheng Wang,Le Song,Yu Li. 2024

[3]A Vegetable-Price Forecasting Method Based on Mixture of Experts. Chenyun Zhao,Xiaodong Wang,Anping Zhao,Yunpeng Cui,Ting Wang,Juan Liu,Ying Hou,Mo Wang,Li Chen,Huan Li,Jinming Wu,Tan Sun. 2025

[4]IPM-AgriGPT: A Large Language Model for Pest and Disease Management with a G-EA Framework and Agricultural Contextual Reasoning. Yuqin Zhang,Qijie Fan,Xuan Chen,Min Li,Zeying Zhao,Fuzhong Li,Leifeng Guo. 2025

[5]Human versus machine: Can generative AI anticipate insect biological control outcomes?. Wyckhuys, Kris A. G.,Akutse, Komivi S.,Amalin, Divina M.,Araj, Salah-Eddin,Beltran, Marie Joy B.,Ben Fekih, Ibtissem,Calatayud, Paul-Andre,Cicero, Lizette,Cokola, Marcellin C.,Colmenarezm, Yelitza C.,Dessauvagesj, Kenza,Dubois, Thomas,Durocher-Grangern, Lena,Fernandez-Triana, Jose L.,Francis, Frederic,Haddi, Khalid,Harrison, Rhett D.,Haseeb, Muhammad,Iwanicki, Natasha S. A.,Jaber, Lara R.,Khamis, Fathiya M.,Legaspi, Jesusa C.,Lomeli-Flores, Refugio J.,Lyu, Baoqian,Montoya-Lerma, James,Nurkomar, Ihsan,O'hara, James E.,Perier, Jermaine D.,Ramirez-Romero, Ricardo,Sanchez-Garcia, Francisco J.,Tavares, Wagner De Souza,Robinson-Baker, Ann Marie S.,Silveira, Luis C. P.,Simeon, Larisner,Solter, Leellen F.,Santos-Amaya, Oscar F.,Trabanino, Rogelio,Valicente, Fernando H.,Vasquez, Carlos,Wang, Zhenying,Zang, Lian-Sheng,Zhang, Wei,Zimba, Kennedy J.,Wu, Kongming,Yubak, D. Gc. 2025

[6]Global agricultural adaptation case database and trend analysis based on large language models. Zhong, Jing-Wen,Zhang, Xue-Yan,Ma, Xin. 2025

[7]Beyond Equations: Large Language Models as a New Frontier for Resilient Ecosystem Modelling. Yu Wu. 2025

作者其他论文 更多>>