Projects •
MicroGenAI
Full Title
Generative Language Models for Unearthing Resilient Microbes in Regenerative AgricultureDescription
This project focuses on the development and evaluation of a Large Language Model (LLM)-based system for automatically extracting relationships between plants, microorganisms, and abiotic stress factors from scientific literature. It compares models, including Llama-3-8B and Mistral-7B, with traditional machine learning approaches, exploring prompting strategies and Retrieval-Augmented Generation (RAG), including knowledge graph-based methods. The aim is to improve scientific information extraction and structuring, supporting the identification of biological interactions that can contribute to more climate-resilient agricultural practices.