A Comprehensive Survey of Retrieval-Augmented Large Language Models for Decision Making in Agriculture: Unsolved Problems and Research Opportunities DOI Open Access
Artem Vizniuk, Grygorii Diachenko, Іvan Laktionov

и другие.

Journal of Artificial Intelligence and Soft Computing Research, Год журнала: 2024, Номер 15(2), С. 115 - 146

Опубликована: Дек. 1, 2024

Abstract The breakthrough in developing large language models (LLMs) over the past few years has led to their widespread implementation various areas of industry, business, and agriculture. aim this article is critically analyse generalise known results research directions on approaches development utilisation LLMs, with a particular focus functional characteristics when integrated into decision support systems (DSSs) for agricultural monitoring. subject integration LLMs DSSs agrotechnical main scientific applied are as follows: world experience using improve processes been analysed; critical analysis carried out, application architectures have identified; necessity focusing retrieval-augmented generation (RAG) an approach solving one limitations which limited knowledge base training data, established; prospects agriculture analysed highlight trustworthiness, explainability bias reduction priority research; potential socio-economic effect from RAG sector substantiated.

Язык: Английский

IPM-AgriGPT: A Large Language Model for Pest and Disease Management with a G-EA Framework and Agricultural Contextual Reasoning DOI Creative Commons

Yuqin Zhang,

Qijie Fan,

Xuan Chen

и другие.

Mathematics, Год журнала: 2025, Номер 13(4), С. 566 - 566

Опубликована: Фев. 8, 2025

Traditional pest and disease management methods are inefficient, relying on agricultural experts or static resources, making it difficult to respond quickly large-scale outbreaks meet local needs. Although deep learning technologies have been applied in management, challenges remain, such as the dependence large amounts of manually labeled data limitations dynamic reasoning. To address these challenges, this study proposes IPM-AgriGPT (Integrated Pest Management—Agricultural Generative Pre-Trained Transformer), a Chinese language model specifically designed for knowledge. The proposed Generation-Evaluation Adversarial (G-EA) framework is used generate high-quality question–answer corpora combined with Agricultural Contextual Reasoning Chain-of-Thought Distillation (ACR-CoTD) low-rank adaptation (LoRA) techniques further optimizes base build IPM-AgriGPT. During evaluation phase, specialized benchmark domain, comprehensively assessing performance tasks. Experimental results show that achieved excellent scores multiple tasks, demonstrating its great potential intelligence management.

Язык: Английский

Процитировано

0
The Role of Generative Artificial Intelligence in Digital Agri-Food DOI Creative Commons
Sakib Shahriar, Maria G. Corradini, Shayan Sharif

и другие.

Journal of Agriculture and Food Research, Год журнала: 2025, Номер unknown, С. 101787 - 101787

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0
Generative AI for Smallholder Agricultural Advice in Sub-Saharan Africa DOI
Joyce Nakatumba‐Nabende, Ann Lisa Nabiryo, Peter Nabende

и другие.

Oxford University Press eBooks, Год журнала: 2025, Номер unknown

Опубликована: Апрель 22, 2025

Abstract Smallholder farmers are prone to food insecurity due the devastating effects of viral crop diseases, pest outbreaks, and lack timely, targeted advice. Leveraging Large Language Models (LLMs) in agriculture offers significant potential bridge information gaps that smallholder face. This study discusses development an expert-reviewed agricultural question-answer dataset. We analysed responses from LLMs experts on crop- animal-related questions using relevancy, coherence, fluency metrics. Our results show GPT-4 outperforms other across these LLM-powered systems can act as virtual extension agents, assisting decision-making overcoming farming challenges.

Язык: Английский

Процитировано

0
Advancements in Agricultural Ground Robots for Specialty Crops: An Overview of Innovations, Challenges, and Prospects DOI Creative Commons
Marcelo Rodrigues Barbosa Júnior,

Regimar Garcia dos Santos,

Lucas de Azevedo Sales

и другие.

Plants, Год журнала: 2024, Номер 13(23), С. 3372 - 3372

Опубликована: Ноя. 30, 2024

Robotic technologies are affording opportunities to revolutionize the production of specialty crops (fruits, vegetables, tree nuts, and horticulture). They offer potential automate tasks save inputs such as labor, fertilizer, pesticides. Specialty well known for their high economic value nutritional benefits, making particularly impactful. While previous review papers have discussed evolution agricultural robots in a general context, this uniquely focuses on application crops, rapidly expanding area. Therefore, we aimed develop state-of-the-art scientifically contribute understanding following: (i) primary areas robots' crops; (ii) specific benefits they offer; (iii) current limitations; (iv) future investigation. We formulated comprehensive search strategy, leveraging Scopus

Язык: Английский

Процитировано

2
The Impact of the EU’s AI Act and Data Act on Digital Farming Technologies DOI

Lucas Ramon Ciutat

Lecture notes in computer science, Год журнала: 2024, Номер unknown, С. 218 - 229

Опубликована: Ноя. 15, 2024

Язык: Английский

Процитировано

0
How do chat apps support the use of farming videos in agricultural extension: A case study from Bihar, India DOI Creative Commons
Sam Coggins, Sugandha Munshi, Jeremy Smith

и другие.

NJAS Impact in Agricultural and Life Sciences, Год журнала: 2024, Номер 97(1)

Опубликована: Дек. 16, 2024

Язык: Английский

Процитировано

0
A Comprehensive Survey of Retrieval-Augmented Large Language Models for Decision Making in Agriculture: Unsolved Problems and Research Opportunities DOI Open Access
Artem Vizniuk, Grygorii Diachenko, Іvan Laktionov

и другие.

Journal of Artificial Intelligence and Soft Computing Research, Год журнала: 2024, Номер 15(2), С. 115 - 146

Опубликована: Дек. 1, 2024

Abstract The breakthrough in developing large language models (LLMs) over the past few years has led to their widespread implementation various areas of industry, business, and agriculture. aim this article is critically analyse generalise known results research directions on approaches development utilisation LLMs, with a particular focus functional characteristics when integrated into decision support systems (DSSs) for agricultural monitoring. subject integration LLMs DSSs agrotechnical main scientific applied are as follows: world experience using improve processes been analysed; critical analysis carried out, application architectures have identified; necessity focusing retrieval-augmented generation (RAG) an approach solving one limitations which limited knowledge base training data, established; prospects agriculture analysed highlight trustworthiness, explainability bias reduction priority research; potential socio-economic effect from RAG sector substantiated.

Язык: Английский

Процитировано

0