Explainability of Large Language Models

8.3209

Dozenten

Beschreibung

Large Language Models (LLMs) have shown extraordinary performance in various domains. Yet, as many deep learning models, the reason and interpretation of this performance remain intransparent, at least to some level.
In this course, we will read, present, and discuss various research papers that aim at explaining and interpreting how LLMs work using different methods.
We will also replicate some of the provided code of the papers and test them in class.

Weitere Angaben

Ort: 50/E08
Zeiten: Do. 14:00 - 16:00 (wöchentlich)
Erster Termin: Donnerstag, 07.11.2024 14:00 - 16:00, Ort: 50/E08
Veranstaltungsart: Seminar (Offizielle Lehrveranstaltungen)

Studienbereiche

• Cognitive Science > Bachelor-Programm
• Cognitive Science > Master-Programm
• Human Sciences (e.g. Cognitive Science, Psychology)