Skip to content Accessibility statement

Large Language Models (LLMA-H) - COM00070H

«Back to module search

  • Department: Computer Science
  • Credit value: 20 credits
  • Credit level: H
  • Academic year of delivery: 2026-27

Module summary

The LLMA module provides a comprehensive introduction to Large Language Models (LLMs), covering their theoretical foundations, together with the architectures and training methods specific to LLMs, and their applications in both practice and research. Students will study how LLMs are trained, fine-tuned, and aligned for diverse applications, including language understanding, language generation, dialogue systems, and knowledge reasoning. The module examines how these models learn and generate content, the challenges of scaling, fine-tuning, and alignment, and the practical and ethical implications for real-world deployment.

The module also considers how LLMs are extended to other modalities, such as image processing: we will introduce Vision-Language Models (VLMs), such as Contrastive Language-Image Pretraining. The reasoning capabilities of modern foundation models, including chain-of-thought prompting, tool use, and structured decision-making are also explored. Through practical labs and assignments, students will gain hands-on experience with leading LLM frameworks, learning how to adapt and apply these models for tasks such as text generation, classification, summarisation, translation, and question answering. Ethical considerations, including bias, fairness, and misuse, will also be addressed to equip students with a critical perspective on explainability as well as responsible LLM development and usage. Practical and ethical implications of explainability in real-world contexts involving a variety of stakeholders - such as systems safety engineering - will be considered in lectures and exercises.

Related modules

Pre-requisite modules

Elective Pre-Requisites

These pre-requisites only apply to students taking this module as an elective.

Deep Learning (COM00049H) and Natural language processing (COM00069H) or equivalent knowledge.

Module will run

Occurrence Teaching period
A Semester 2 2026-27

Module aims

This module aims to provide students with an in-depth understanding of Large Language Models and the implications of their deployment in real-world situations. This will provide the basis for informed, critical understanding of the potential and limitations of the technologies, and the ethical considerations involved in ethical development and use of LLM-based technologies.

The module will consider the theoretical foundations and architectural strategies for LLMs in general, and will consider how they can be refined for a variety of real-world applications, with a particular focus on explainability. The extension of LLM technologies into other modalities - such as Vision-Language Modules - will be explored. There will be consideration of the selection and development of appropriate evaluation approaches for specific application domains, and students will gain an understanding of the challenges, limitations and implications inherent in real-world deployment of the current technologies.

Module learning outcomes

  • Explain and critically assess the theoretical foundations and architectures underpinning large language models and vision-language models as well as the latest chain-of-thought reasoning methods.

  • Describe and critically evaluate training, fine-tuning, and alignment techniques used in the development of LLMs for diverse applications with a focus on explainability and the challenge of developing appropriate evaluation metrics and their limitations.

  • Apply LLMs to practical tasks such as text generation, summarisation, translation, and question answering using modern frameworks.

  • Discuss the challenges and implications of deploying large-scale models with regards to issues of scalability.

  • Discuss, measure and interpret the energy consumption and environmental impact of training and deploying LLMs to make informed, sustainable decisions in model development and deployment.

  • Identify and address ethical concerns related to bias, fairness, and responsible use of LLMs in a variety of real-world scenarios.

Indicative assessment

Task % of module mark
Essay/coursework 100.0

Special assessment rules

None

Indicative reassessment

Task % of module mark
Essay/coursework 100.0

Module feedback

Feedback is provided through work in practical sessions, and after the final assessment as per normal University guidelines.

Indicative reading

TBD



The information on this page is indicative of the module that is currently on offer. The University constantly explores ways to enhance and improve its degree programmes and therefore reserves the right to make variations to the content and method of delivery of modules, and to discontinue modules, if such action is reasonably considered to be necessary. In some instances it may be appropriate for the University to notify and consult with affected students about module changes in accordance with the University's policy on the Approval of Modifications to Existing Taught Programmes of Study.