| Code |
16676
|
| Year |
2
|
| Semester |
S1
|
| ECTS Credits |
6
|
| Workload |
PL(30H)/T(30H)
|
| Scientific area |
Informatics
|
|
Entry requirements |
Students are expected to have a foundational understanding of programming, preferably in Python, as well as basic knowledge of artificial intelligence and machine learning concepts. Prior experience with natural language processing (NLP) or deep learning frameworks, such as PyTorch, is beneficial but not mandatory.
|
|
Learning outcomes |
By the end of this course, students will be able to design, evaluate, and optimize prompts for large language models (LLMs) across different applications. They will understand key concepts such as prompt structure, context management, and model biases, as well as advanced techniques like chain-of-thought prompting and role-based instructions. Additionally, students will develop critical thinking skills for assessing model responses and iterating on prompt designs to improve performance in real-world tasks.
|
|
Syllabus |
Introduction to Prompt Engineering: Principles, Applications, and Challenges
Structure and Components of Effective Prompts
Context Management and Role-Playing Strategies
Advanced Prompting Techniques: Chain-of-Thought, Few-Shot Learning, and Meta-Instructions
Evaluating and Refining Prompts: Metrics, Biases, and Ethical Considerations
Real-World Applications: Automating Tasks, Enhancing Creativity, and Decision Support
Hands-on Labs: Practical Implementation with LLM APIs and Fine-Tuning Strategies
|
|
Main Bibliography |
Brian Roemmele, The Art of Prompt Engineering
OpenAI, GPT Best Practices Guide (online resource)
Lilian Weng, Prompt Engineering Techniques & Applications (blog articles)
Papers and articles on NLP and LLM prompting strategies from ACL, NeurIPS, and other AI conferences
|
|
Teaching Methodologies and Assessment Criteria |
The course follows a blended learning approach, combining theoretical lectures, interactive discussions, and hands-on practical sessions. Assessment is based on class participation, individual and group projects, and a final evaluation that includes both a written test and a prompt engineering challenge. Students must demonstrate proficiency in designing and optimizing prompts for diverse use cases.
|
|
Language |
Portuguese. Tutorial support is available in English.
|