You’ve probably used tools like ChatGPT or Microsoft Copilot to help brainstorm an idea, plan an upcoming trip or view your horoscope, but have you ever wondered what powers these tools? They are built on something called a Large Language Model (LLM).
LLMs are a type of advanced artificial intelligence (AI) designed to understand and generate human-like text. They’re trained on massive amounts of text, typically scraped from the internet, so they can respond to questions, summarize information, write stories and even assist with complex tasks like coding or medical documentation.
Some of the most well-known LLMs today include GPT-4o, Claude 3, Gemini 1.5 and LLaMA 3, to name a few. These models are transforming how we interact with technology, making it more natural, intuitive and powerful.
At the University of Colorado Anschutz Medical Campus, researchers are using LLMs to summarize patient records, generate clinical notes and even assist in patient diagnosis. To better understand what an LLM is and how it works, we sat down with Yanjun Gao, PhD, assistant professor of biomedical informatics.