Module manager: Dr Noorhan Abbas
Email: N.H.Abbas@leeds.ac.uk
Taught: 1 May to 30 Jun (2mth)(adv yr), 1 May to 30 June, 1 Nov to 31 Dec, 1 Nov to 31 Dec (2mth)(adv yr) View Timetable
Year running 2026/27
N/A
None
This module is not approved as an Elective
This module explores how deep learning methods enable machines to process, understand, and generate human language. It examines how modern language models are built and trained, how they align with human intent, and how their memory and retrieval mechanisms can improve factual grounding and reduce hallucination. Students study how large language models form the backbone of contemporary language technologies and underpin emerging developments in autonomy, orchestration, and agentic artificial intelligence (AI).
This module aims to develop a comprehensive understanding of how deep learning methods enable machines to represent, interpret, and generate human language. It builds on the principles of representation learning and sequence modelling to explore the architectures, training dynamics, and scaling processes that underpin modern language models. Students investigate how such models learn structure and meaning from text, how alignment and grounding enhance reliability and factual consistency, and how memory, retrieval, and adaptation extend their capability over time. The module also examines how large language models serve as the foundation for systems exhibiting elements of autonomy, orchestration, and agentic AI. By engaging critically and practically with these technologies, students develop the knowledge and confidence to navigate and contribute to the evolving landscape of modern AI. Learning activities combine concise explanations, guided demonstrations, and practical experimentation with natural language models to consolidate both conceptual and applied understanding.
On successful completion of the module students will have demonstrated the following learning outcomes relevant to the subject:
1. Explain how deep learning architectures represent, interpret, and generate human language.
2. Apply natural language models to tasks such as text classification, translation, summarisation, and generation.
3. Discuss how scaling, alignment, grounding, and memory mechanisms influence the performance and reliability of large language models.
4. Evaluate the factors contributing to model hallucination, bias, and factual consistency in language generation.
5. Develop simple agentic AI applications by combining large language models with external tools or structured reasoning processes to perform goal-directed tasks.
On successful completion of the module students will have demonstrated the following skills learning outcomes:
1. Apply analytical and structured problem-solving skills to design, implement, and evaluate NLP solutions for complex textual data.
2. Demonstrate adaptability and self-directed learning by integrating new tools, techniques, or frameworks to address evolving challenges in NLP.
3. Communicate technical concepts, processes, and insights clearly to both technical and non-technical audiences using appropriate documentation and visualisation.
4. Apply integrated problem-solving and systems thinking to develop and evaluate NLP solutions.
5. Exercise reflective practice and critical evaluation to assess methods, interpret results, and continuously improve performance.
Indicative content for this module includes:
- Foundations of natural language processing and representation learning for text
- Sequence modelling with recurrent and transformer-based architectures
- Pretraining, fine-tuning, and adaptation strategies for language models
- Retrieval-augmented generation and other grounding methods to improve factual accuracy and context use
- Introduction to agentic AI through goal-directed applications that integrate language models with structured workflows
| Delivery type | Number | Length hours | Student hours |
|---|---|---|---|
| Discussion forum | 6 | 1 | 6 |
| WEBINAR | 6 | 1 | 6 |
| Independent online learning hours | 42 | ||
| Private study hours | 96 | ||
| Total Contact hours | 12 | ||
| Total hours (100hr per 10 credits) | 150 | ||
1. Webinar-Based Discussion and Q&A
2. Weekly Practical Exercises
| Assessment type | Notes | % of formal assessment |
|---|---|---|
| Online Assessment | ~20 questions about different scenarios | 20 |
| Coursework | Coursework Project - Technical Report | 80 |
| Total percentage (Assessment Coursework) | 100 | |
This module will be reassessed through a 100% individual assessment in the same format as Assessment 2 (coursework project). The reassessment will involve a practical project that requires students to apply and integrate the knowledge and skills developed across all learning outcomes.
Check the module area in Minerva for your reading list
Last updated: 30/04/2026
Errors, omissions, failed links etc should be notified to the Catalogue Team