Hauptinhalt
Topinformationen
Lehrende
Explainability of Large Language Models
DozentIn: Ulf Krumnack, Ph.D. , Prof. Dr. phil. Kai-Uwe Kühnberger
Veranstaltungstyp: Seminar
Ort: 69/117
Zeiten: Fr. 14:00 - 16:00 (wöchentlich)
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.
