Name: Harnessing Large Language Models for Reproducible and Controlled Data Extraction
Start: 2026-09-17T15:00:00+01:00
End: 2026-09-17T17:00:00+01:00

🎉 **Event Announcement: UNILORIN R Users Group Meetup Series**
📌 **Event Theme:** Harnessing Large Language Models for Reproducible and Controlled Data Extraction
📅 **Date:** Thursday, September 17, 2026
⏰ **Time:** 3 PM WAT
📍 **Venue:** YouTube Live

Join us for another insightful session in the **UNILORIN R Users Group Meetup Series**.

This session will demonstrate how to harness the capabilities of large language models (LLMs) in a reproducible and controlled way. In particular, Francisco will show how LLMs can be used to extract structured information from unstructured data, such as interview transcripts, using R and the **ellmer** package. The session will focus on developing a transparent, reproducible workflow that allows researchers to use LLMs systematically while maintaining control over the data extraction process and outputs.

Ogundepo Ezekiel

Dr. Samuel Farohunbi

Dr. MK Garba

University of Ilorin R Users Group

R User Groups

R Consortium

Technology

Functional Programming

Programming in R

Data Science

Data Science using R

Big Data

Data Science for Business

Clinical Data Science

Data Science for Healthcare

Machine Learning

Data Mining

Francisco Cardozo is a researcher passionate about harnessing data, technology, and innovation to advance prevention science. His work focuses on developing and evaluating programmes that prevent health challenges, with a particular interest in how artificial intelligence can strengthen intervention design and implementation.

A strong advocate for open-source research and transparent science, Francisco contributes tools and resources that make research more accessible and reproducible. His mission is to bridge innovation and public health to create meaningful, sustainable impact.

Francisco Cardozo