FF:CORE139 Large Language Models in Pract - Course Information
CORE139 Large Language Models in Practice
Faculty of ArtsAutumn 2025
- Extent and Intensity
- 2/0/0. 3 credit(s). Type of Completion: k (colloquium).
- Teacher(s)
- Mgr. et Mgr. Markéta Audy Masopustová (lecturer)
Mgr. Marek Grác, Ph.D. (lecturer)
Mgr. Hana Žižková, Ph.D. (lecturer) - Guaranteed by
- Mgr. Hana Žižková, Ph.D.
Department of Czech Language – Faculty of Arts
Contact Person: Mgr. Hana Žižková, Ph.D.
Supplier department: Department of Czech Language – Faculty of Arts - Prerequisites
- TYP_STUDIA(BM) && FORMA(P)
The course is open to students in the full-time Bachelor's and five-year Master's cycle. - Course Enrolment Limitations
- The course is offered to students of any study field.
The capacity limit for the course is 100 student(s).
Current registration and enrolment status: enrolled: 0/100, only registered: 0/100, only registered with preference (fields directly associated with the programme): 0/100 - Course objectives
- The aim of the course is to provide students from various disciplines with a basic understanding of working with large language models and their applications in their own fields. Students will work in groups of four on projects that require the use of LLM to solve specific problems or create applications for their field. These projects will emphasize collaboration between students from different disciplines. Submission and defense of the project is a requirement for successful completion of the course.
- Learning outcomes
- Upon completion of the course, the student will be able to: *understand the basic principles on which models are based * identify areas of application of LLM in their field of study * make effective use of agile engineering techniques * understand the ethical issues associated with the use of AI * conduct a practical experiment related to the use of LLM with appropriate evaluation
- Syllabus
- *Fundamental problems of LLM systems. Why do they hallucinate and fail to master even simple mathematics? * Ethics, regulation (Act of AI), bias/stereotypes and censorship of outputs. * Possibilities of extending existing LLMs with current data (textual, measurement results, ...). * Differences between existing approaches to LLM from a power-user perspective. * Vulnerability of LLMs and possibilities of attacks on them, jailbreak. * Exploitation of APIs and third party service calls. * Usability for text creation, translation and editing. * Meaningfulness of using LLM vs. creating your own specialized ML model.
- Teaching methods
- Students will be encouraged to share their knowledge and perspectives and seek synergies between different disciplines. Working on the project will give students the opportunity not only to apply theoretical knowledge in practice, but also to develop collaborative, creative and critical thinking skills in an interdisciplinary environment.
- Assessment methods
- Submitting and defending the project is a condition for successful completion of the course.
- Language of instruction
- English
- Enrolment Statistics (Autumn 2025, recent)
- Permalink: https://is.muni.cz/course/phil/autumn2025/CORE139