Large language models and agricultural extension services

Paper by Asaf Tzachor, M. Devare, Catherine Richards, P. Pypers, A. Ghosh, J. Koo, S. Johal, B. King
Published on 06 November 2023


Several factors have traditionally hampered the effectiveness of agricultural extension services, including limited institutional capacity and reach. Here we assess the potential of large language models (LLMs), specifically Generative Pre-trained Transformer (GPT), to transform agricultural extension. We focus on the ability of LLMs to simplify scientific knowledge and provide personalized, location-specific and data-driven agricultural recommendations. We emphasize shortcomings of this technology, informed by real-life testing of GPT to generate technical advice for Nigerian cassava farmers. To ensure a safe and responsible dissemination of LLM functionality across farming worldwide, we propose an idealized LLM design process with human experts in the loop.

Read full paper

Subscribe to our mailing list to get our latest updates