Grounding Medical Q&A using ChatGPT plugins and Knowledge Graphs

Grounding Medical Q&A using ChatGPT plugins and knowledge graphs creates a powerful tool that can assist healthcare professionals access, interact with, and utilize the latest medical information.

In this on-demand demonstration, GenomOncology’s Chief Technology Officer, Ian Maurer, discusses the use of ChatGPT plugins and Knowledge Graphs to ground medical Q&A and reduce hallucinations in large language models (LLM). In this video, learn more about how: 

• Medical Q&A is a dataset used to test the performance of models answering medical questions. 

• LLMs are prone to hallucinations due to a limited understanding, data limitations, and no real-time interaction capability. 

• Grounding strategies include pre-training and fine-tuning, prompt engineering, and similarity search to provide more context and improve the model’s performance.

• Knowledge graphs can augment LLM’s performance by providing access to databases of specialized fields like genomics.

Interested in learning more? Connect with Ian today.