Abstract: One of the frequent points in the mainstream narrative about large language models is that they have "emergent properties" (sometimes even dangerous enough to be considered existential risk to mankind). However, there is much disagreement about even the very definition of such properties. If they are understood as a kind of generalization beyond training data - as something that a model does without being explicitly trained for it - I argue that we have not in fact established the existence of any such properties, and at the moment we do not even have the methodology for doing so.
Bio: Anna Rogers is an Associate Professor in the Computer Science Department at the IT University of Copenhagen, affiliated with the NLPNorth section. Her main research area is Natural Language Processing, in particular analysis and evaluation of pre-trained language models. She is currently an editor-in-chief of ACL Rolling Review, the peer review platform for all major NLP conferences.
Location: Attend in person at room J411 or via Zoom, https://gu-se.zoom.us/j/66299274809?pwd=Yjc2ejc2VVhraXVJMmhWeWtOQ2NuUT09
Time: 13:15-15:00