HomeChatGPT for Researchers
cover image

ChatGPT for Researchers

Elective Course for PhD Students at University of Ljubljana

Join us for a comprehensive exploration of ChatGPT and similar large language models! This course will explain their training and mechanics, and demonstrate how they can assist in research by providing information access, sparking creativity, generating ideas, and summarizing complex concepts. You'll learn prompt engineering to enhance your research projects, dive into data analysis, and understand how to integrate new material for improved outcomes. We will also explore retrieval augmented generation to expand the capabilities of these models. After the course, you will get in-depth understanding of how to use large language models and will, for example, know how to:

  • Transform ChatGPT into a topic-practicing tool for in-depth understanding.
  • Craft prompts to inquire about your research and structure comprehensive research reports.
  • Use large language models to explain your research topic to a general audience.
  • Grade homework assignments with the assistance of a large language model.
  • Turn ChatGPT into your presentation advisor to structure and enhance your presentations.
  • Generate literature reviews by summarizing and synthesizing relevant research papers.
  • Develop creative brainstorming sessions to explore new research ideas and hypotheses.
  • Automate the creation of detailed and organized research outlines.
  • Enhance grant proposals by refining and optimizing your submissions.
  • Simulate peer review to receive constructive feedback on your drafts.
  • Generate and manage bibliographies and citations effortlessly.
  • Create quizzes and educational materials to test understanding of your research topics.

Type of course: Lectures + Homework Assignments

Type of course: Lectures + Homework Assignments

Course Code: 63835F (UL FRI)

ECTS: 5

Course name in Slovenian: ChatGPT za raziskovalce

Location for lectures: Faculty of Computer and Information Science, University of Ljubljana, Večna pot 113, Ljubljana

Time of the Lectures: The lectures are expected to take place in November and December of 2024 and January 2025. While we anticipate that they will be held in the evenings, likely between 5:00 PM and 7:00 PM, the exact schedule and room details will be confirmed in late October. This timing will be finalized once the undergraduate schedule at the University of Ljubljana is set and enrollment for this course is complete.

Prerequisites: No prior knowledge of large language models or computer programming is assumed. This is an introductory course intended for a general audience. Students from humanities, social sciences, natural sciences, and engineering are welcome.

Language: All course materials and lectures will be conducted in English.

Course Content

This is a machine learning and AI course intended for non-computer science students. We particularly encourage students from social sciences, humanities, natural sciences, engineering, and arts to enroll. The course has a gentle learning curve, with additional material and lecture notes available for all students. The course covers the following topics:

Lecture 1: Understanding Large Language Models

  • Explore the evolution from logistic regression to deep neural networks.
  • Gain insights into the structure and functionality of large language models.
  • What is generative AI and how it works?

Lecture 2: Data Science on Text: Finding Similar Words and Documents

  • Practical exercise: text embedding, finding similar text documents, exploratory data analysis of text corpus, document maps.
  • Case study: clustering of words.
  • Case study: exploratory analysis of daily news.

Lecture 3: Introduction to Prompt Engineering

  • Understand the basics of prompt engineering.
  • Learn how to structure prompts and define personas.
  • Explore various use cases such as new information retrieval.
  • Case study: flipped interaction for writing a grant proposal.

Lecture 4: Advanced Prompting Patterns

  • Refine questions and enhance cognitive understanding through audience personas.
  • Prompts that define the structure of conversation.
  • Practice few-shot examples with sentiment analysis and product reviews.
  • Learn grading and explanation techniques with template patterns.
  • Explore chain of thought prompting for proven reasoning and cognitive verification.

Lecture 5: Data Analysis and Retrieval Augmented Generation

  • Analyze new documents.
  • Structured analysis of new documents.
  • Data analysis with LLM, reporting.
  • State-of-the-art: what is retrieval augmented generation?
  • How to construct your own chatbot?

Lecturer

Prof. Dr. Blaž Zupan teaches artificial intelligence and machine learning at the University of Ljubljana and Baylor College of Medicine. His research has focused on explainable AI and combinations of machine learning and data visualization techniques. He runs a twenty-member bioinformatics laboratory, which also develops Orange, a comprehensive open-source toolbox for machine learning.

Enrollment Information

This is an elective course offered to all students at the University of Ljubljana. Students need to enroll at their own Faculty, which will then send their enrollment information to the Faculty of Computer and Information Science.

Course Materials

All course materials will be provided at the start of the course and will be available on the course's homepage (Moodle). The materials include lecture notes, short optional educational videos, and quizzes. We will provide course material to the students upon enrollment.

Homework Assignments and Grading

The course will include practical homework assignments. Assignments will be submitted through either quiz-like questionnaires or written reports.

The final grade for the course will be computed based on scores from the homework assignments. There will be no final exam.

Course Attendance

This course is primarily organized for on-site attendance to facilitate direct interaction and engagement during lectures. However, we understand that circumstances may occasionally prevent students from attending in person. In such cases, ample resources, including lecture notes, videos, and relevant literature, will be provided to support your learning and help you successfully complete the required home assignments. Additionally, some lectures may be recorded and made available online to ensure you have access to the necessary material to stay on track with the course.

Contact Information, On-Line Support, and Further Announcements

Join our Discord server for any questions or further information about the course.

Discord Icon

Chapters