Large Language Models: Do it yourself

On Thursday, September 28^th, Professor Antal van den Bosch invites you to explore the utilization of the latest open-source Large Language Models (LLMs) for research. This lecture, organized by the Centre for Digital Humanities is open to everyone.

LLMs are the driving force behind chatbots like ChatGPT. Thanks to platforms like Huggingface, both closed and open-source LLMs have become increasingly accessible for research purposes.

During this lecture, Van den Bosch will explore various applications of open LLMs. For example, how a pretrained LLM for the Dutch language, named RobBERT, can be tested on existing cloze test data, as it is trained on masked word prediction; and how BART, a transformer for text-to-text processing, can be fine-tuned to become a Dutch spelling corrector. Additionally, Van den Bosch will address one of the key hurdles in being able to flexibly work with LLMs: The sparse availability of GPUs and the energy-consuming deep learners.

This lecture offers a hybrid format, allowing you the choice to attend at the Digital Humanities Workspace (0.32) in the University Library City Centre or participate online via Teams.