Michael Rowe

Trying to get better at getting better

Customising language models with your own data

Large language models like GPT-4 and ChatGPT can generate high-quality text that is useful for many applications, including chatbots, language translation, and content creation. However, these models are limited to the information contained within their training datasets… To solve this problem, we can augment our LLMs with our own custom documents.

Dickson, B. (2023, May 1). How to customize LLMs like ChatGPT with your own data and documents. TechTalks.

In addition to using personal documents to customise the model, we could embed all the university’s regulations, for example. Or, all the NMC standards. Imagine being able to query large text corpora, using natural language? What might we learn about our organisational and professional contexts?


Share this


Discover more from Michael Rowe

Subscribe to get the latest posts to your email.