English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large language models (LLMs) have demonstrated remarkable capabilities innatural language understanding across various domains, including healthcare andfinance. For some tasks, LLMs achieve similar or better performance thantrained human beings, therefore it is reasonable to employ human exams (e.g.,certification tests) to assess the performance of LLMs. We present acomprehensive evaluation of popular LLMs, such as Llama 2 and GPT, on theirability to answer agriculture-related questions. In our evaluation, we alsoemploy RAG (Retrieval-Augmented Generation) and ER (Ensemble Refinement)techniques, which combine information retrieval, generation capabilities, andprompting strategies to improve the LLMs' performance. To demonstrate thecapabilities of LLMs, we selected agriculture exams and benchmark datasets fromthree of the largest agriculture producer countries: Brazil, India, and theUSA. Our analysis highlights GPT-4's ability to achieve a passing score onexams to earn credits for renewing agronomist certifications, answering 93% ofthe questions correctly and outperforming earlier general-purpose models, whichachieved 88% accuracy. On one of our experiments, GPT-4 obtained the highestperformance when compared to human subjects. This performance suggests thatGPT-4 could potentially pass on major graduate education admission tests oreven earn credits for renewing agronomy certificates. We also explore themodels' capacity to address general agriculture-related questions and generatecrop management guidelines for Brazilian and Indian farmers, utilizing robustdatasets from the Brazilian Agency of Agriculture (Embrapa) and graduateprogram exams from India. The results suggest that GPT-4, ER, and RAG cancontribute meaningfully to agricultural education, assessment, and cropmanagement practice, offering valuable insights to farmers and agriculturalprofessionals.

GPT-4 as an Agronomist Assistant? Answering Agriculture Exams Using Large Language Models