Teaching LLMs at Charles University: Assignments and Activities

TL;DR

This paper details a new university course on large language models, including practical assignments like weather report generation and machine translation, along with engaging classroom activities to enhance learning.

Contribution

It introduces a comprehensive set of teaching materials and activities specifically designed for instructing students on large language models at the university level.

Findings

Students gain hands-on experience with LLM inference tasks.

Interactive activities improve understanding of research papers.

Assignments demonstrate practical applications of LLMs.

Abstract

This paper presents teaching materials, particularly assignments and ideas for classroom activities, from a new course on large language models (LLMs) taught at Charles University. The assignments include experiments with LLM inference for weather report generation and machine translation. The classroom activities include class quizzes, focused research on downstream tasks and datasets, and an interactive "best paper" session aimed at reading and comprehension of research papers.