| Unit name | Theory and Practice of Large Language Models |
|---|---|
| Unit code | SEMTM0048 |
| Credit points | 20 |
| Level of study | M/7 |
| Teaching block(s) |
Teaching Block 2 (weeks 13 - 24) |
| Unit director | Dr. Aitchison |
| Open unit status | Not open |
| Units you must take before you take this one (pre-requisite units) |
None |
| Units you must take alongside this one (co-requisite units) |
None |
| Units you may not take alongside this one |
None |
| School/department | School of Engineering Mathematics and Technology |
| Faculty | Faculty of Science and Engineering |
Why is this unit important?
Modern AI cannot be understood without large language models (LLMs). This unit gives a broad overview of LLMs in the context of modern AI. There is an emphasis on the fundamental techniques and algorithms, along with discussion of applications across a range of disciplines.
How does this unit fit into your programme of study
You will build on your existing understanding of LLMs, acquired in the in foundational units, to develop an understanding of LLMs in AI, and their mathematical and computational underpinnings. The course prepares students not only for research- or application-oriented MSc projects during the summer, but also for future activities in their careers as AI specialists, engineers or researchers.
An overview of content
Throughout the unit there is a focus on students understanding theory and modelling principles in order to apply them effectively to LLMs. You will gain a refined understanding of different LLM architectures, pre- and post-training concepts, LLM inference, and how to effectively use modern LLMs in a variety of domains.
How will students, personally, be different as a result of the unit
At the end of the unit, you will be able to effectively apply and fine-tune LLMs to a range of specific problems, and to apply these principles to other AI tasks.
Learning outcomes
On successful completion of this unit, you will be able to:
You will learn through a range of synchronous and asynchronous activities including lectures and problem classes/computer laboratories. Problem classes/computer laboratories will be used to provide direct feedback on linked exercises.
Tasks which help you learn and prepare you for summative tasks (formative):
The lecture notes will provide questions and worked answers. Additionally, some of the practical lab sheets will provide exercises and worked answers. Feedback on these questions and exercises will be provided by a combination of laboratory/problem classes and Q&A sessions.
Tasks which count towards your unit mark (summative):
The assessment for this course consists of two main components. First, there is an in-person exam (50%) designed to evaluate understanding of the foundational concepts and techniques introduced in the unit, with particular focus on ILOs 1 and 2. Alongside this, students will complete an open-ended group coursework project (50%) aligned with ILOs 3 and 4, where they are encouraged to explore an application of AI of their choosing, demonstrate creativity and critical engagement, and present their work in the style of an academic paper.
When assessment does not go to plan:
When required by the Board of Examiners, you will normally complete reassessments in the same formats as those outlined above. If you need to resit the group assessment component, it will be replaced by an individual task with a proportional level of complexity, which may be linked to the original topic of the assessment or require a reflection on the role of collaborative work in the project. However, the Board may modify the form or number of reassessments required. Details of reassessments are normally confirmed by the School shortly after the notification of your results at the end of the academic year.
If this unit has a Resource List, you will normally find a link to it in the Blackboard area for the unit. Sometimes there will be a separate link for each weekly topic.
If you are unable to access a list through Blackboard, you can also find it via the Resource Lists homepage. Search for the list by the unit name or code (e.g. SEMTM0048).
How much time the unit requires
Each credit equates to 10 hours of total student input. For example a 20 credit unit will take you 200 hours
of study to complete. Your total learning time is made up of contact time, directed learning tasks,
independent learning and assessment activity.
See the University Workload statement relating to this unit for more information.
Assessment
The assessment methods listed in this unit specification are designed to enable students to demonstrate the named learning outcomes (LOs). Where a disability prevents a student from undertaking a specific method of assessment, schools will make reasonable adjustments to support a student to demonstrate the LO by an alternative method or with additional resources.
The Board of Examiners will consider all cases where students have failed or not completed the assessments required for credit.
The Board considers each student's outcomes across all the units which contribute to each year's programme of study. For appropriate assessments, if you have self-certificated your absence, you will normally be required to complete it the next time it runs (for assessments at the end of TB1 and TB2 this is usually in the next re-assessment period).
The Board of Examiners will take into account any exceptional circumstances and operates
within the Regulations and Code of Practice for Taught Programmes.
