Unit 4: Current research

Published

November 7, 2025

In this unit, you will see several examples of current research on large language models. The unit features both lecture-style reviews of recent developments and videos from research presentations.

Lectures

The lectures start by exploring how LLMs might store factual information. You will then learn about efficient fine-tuning techniques, retrieval-augmented generation, multilingual transformer architectures, and the issue of data contamination. The series concludes by reflecting on the “stochastic parrots” debate.

Section Title Video Slides Quiz
4.1 How might LLMs store facts? video none quiz
4.2 Efficient fine-tuning video paper quiz
4.3 Retrieval-augmented generation (until 17:50) video none quiz
4.4 Multilinguality and modular transformers video paper quiz
4.5 Data contamination video paper quiz
4.6 LLMs as stochastic parrots (until 15:00) video none quiz
ImportantQuiz deadline

To earn a wildcard for this unit, you must complete the quizzes no later than 2025-11-25.

Online meeting

During the online meeting, we will see additional examples of current research on LLMs.

TipMeeting details

The meeting will take place on 2025-11-26 between 18:00–20:00. A Zoom link will be sent out via the course mailing list.

Lab

In this lab, you will implement LoRA, one of the most well-known methods for parameter-efficient fine-tuning of large language models. Along the way, you will earn experience with Hugging Face Transformers, a state-of-the-art library for training and deploying language models, as well as with several related libraries.

Link to the lab