Advanced Uses of LLMs

In Person
Large Language Models like GPT-4, Claude, and Google's Gemini are powerful AI tools that can generate human-like text. However, these models are prone to hallucinations and have limited knowledge that can quickly become outdated. To address these limitations, researchers have developed techniques for augmenting and expanding the knowledge base of these AI systems.
This course will introduce participants to methods of expanding Large Language Model knowledge. The course covers context window injection, Retrieval Augmented Generation (RAG), and an introduction to fine-tuning. The goal is to teach participants how to understand and practically implement knowledge augmentation techniques for AI systems.
This is an advanced-level training. An understanding of how to create and run Python code in notebooks is required and experience using data-science libraries like Pandas and NumPy will allow you to get more out of the course.
Those who have registered to take part will receive an email with full details on how to get ready for this course.
This course will be taught by Martin Disley.
After taking part in this event, you may decide that you need some further help in applying what you have learnt to your research. If so, you can book a Data Surgery meeting with one of our training fellows.
More details about Data Surgeries.
If you’re new to this training event format, or to CDCS training events in general, read more on what to expect from CDCS training. Here you will also find details of our cancellation and no-show policy, which applies to this event.
Learning Outcomes:
• Understand limitations of LLM knowledge
• Compare and contrast approaches to LLM knowledge integration
• Construct a working Retrieval Augmented Generation (RAG) system
Knowledge refreshment pre-reading suggestions:
If you're interested in other training on machine learning and AI have a look at the following:
- Digital Method of the Month: Machine Learning
- An Introduction to Machine Learning
- Regression and Mixed Effects Modelling
- Silent Disco: Hackers' Guide to Language Models
- Digital Method of the Month: What LLM Can and Cannot Do
Return to the Training Homepage to see other available events.
Room 4.35, Edinburgh Futures Institute
This room is on Level 4, in the North East side of the building.
When you enter via the level 2 East entrance on Middle Meadow Walk, the room will be on the 4th floor straight ahead.
When you enter via the level 2 North entrance on Lauriston Place underneath the clock tower, the room will be on the 4th floor to your left.
When you enter via the level 0 South entrance on Porters Walk (opposite Tribe Yoga), the room will be on the 4th floor to your right.