Explore UCD

UCD Home >

POL42560

Academic Year 2024/2025

AI and Large Language Models (POL42560)

Subject:
Politics
College:
Social Sciences & Law
School:
Politics & Int Relations
Level:
4 (Masters)
Credits:
10
Module Coordinator:
Assoc Professor James Cross
Trimester:
Spring
Mode of Delivery:
On Campus
Internship Module:
No
How will I be graded?
Letter grades

Curricular information is subject to change.

Large language models (LLMs), such as those behind tools like ChatGPT, have garnered significant attention in the media for their ability to generate human-like text, sparking both enthusiasm and debate about their implications for various fields. For social scientists, LLMs offer a potentially useful approach to processing and interpreting vast amounts of data, enhancing our ability to study complex societal issues. This course offers an interdisciplinary approach to understanding and applying LLMs in social and political science, with a focus on text analysis. It combines theoretical foundations with practical, hands-on experience in applying LLMs to address substantive social science questions. Students will explore the capabilities and limitations of LLMs and engage critically with issues such as bias, environmental impact, misinformation, and intellectual property rights. They will also become familiar with essential research practices including documentation, reproducibility, and validation. This course is designed for students with or without experience in Python or a similar programming language, but a willingness to learn quickly and engage with technical content is essential. It aims to equip them with the skills and knowledge needed to effectively apply AI in social science research.

About this Module

Learning Outcomes:

By the end of the course, students will be able to:
1. Understand the fundamentals of large language models and their applications in social sciences.
2. Implement LLMs for various tasks relevant to political and social science research using Python.
3. Critically evaluate the ethical and societal implications of AI technologies, particularly LLMs, in the context of social science.
4. Apply best practices in research documentation, reproducibility, and validation when using AI tools.
5. Engage in informed discussions about the impact of AI on society, including issues of bias, sustainability, and concentration of power.

Indicative Module Content:

- Using Python and APIs for programming tasks with the help of AI tools (GitHub Copilot)
- Effective use of development environments (VSCode, Jupyter Notebook) and version control systems (Git)
- Fundamentals of LLMs, pretraining, fine-tuning, and transformer-based models
- LLM applications including classification, transcription, and topic modelling
- Research best practices: reproducibility, validation, and documentation
- Ethical implications: bias, misinformation, environmental impact, training data ownership, and copyright in AI-generated content
- An introduction to advanced techniques, which may include quantisation, parameter-efficient fine-tuning (PEFT), retrieval-augmented generation (RAG) and multimodal models
- Future challenges and regulation

Student Effort Hours:
Student Effort Type Hours
Lectures

24

Autonomous Student Learning

200

Total

224


Approaches to Teaching and Learning:
- Seminar discussions
- Project-based learning
- Peer-reviewed research project

Requirements, Exclusions and Recommendations

Not applicable to this module.


Module Requisites and Incompatibles
Not applicable to this module.
 

Assessment Strategy
Description Timing Component Scale Must Pass Component % of Final Grade In Module Component Repeat Offered
Group Work Assignment: Group presentations Week 11, Week 12 Graded No
25
No
Group Work Assignment: Group project Week 3, Week 4, Week 5, Week 6, Week 7, Week 8, Week 9, Week 10, Week 11, Week 12 Graded No
50
No
Reflective Assignment: Project reflection Week 11, Week 12, Week 14, Week 15 Graded No
25
No

Carry forward of passed components
No
 

Remediation Type Remediation Timing
In-Module Resit Prior to relevant Programme Exam Board
Please see Student Jargon Buster for more information about remediation types and timing. 

Feedback Strategy/Strategies

• Group/class feedback, post-assessment
• Self-assessment activities

How will my Feedback be Delivered?

Not yet recorded.

Timetabling information is displayed only for guidance purposes, relates to the current Academic Year only and is subject to change.
Spring Lecture Offering 1 Week(s) - 20, 21, 22, 23, 24, 25, 26, 29, 30, 31, 32, 33 Wed 09:00 - 10:50