4 papers
When Behavioral Safety Evaluation Fails: A Representation-Level Perspective
Enyi Jiang, Anders Gjølbye, Anders Gjølbye +2
Safety evaluation of large language models (LLMs) is largely behavioral: a model is certified safe when it refuses harmful requests and answers benign ones. But refusing on the pro…
Reasoning Models Don't Just Think Longer, They Move Differently
Anders Gjølbye, Lars Kai Hansen, Sanmi Koyejo
Reasoning-trained language models often spend more tokens on harder problems, but longer chains of thought do not show whether a model is merely computing for more steps or followi…
Missing-Data-Induced Phase Transitions in Spectral PLS for Multimodal Learning
Anders Gjølbye, Ida Kargaard, Emma Kargaard +2
Partial Least Squares (PLS) learns shared structure from paired data via the top singular vectors of the empirical cross-covariance (PLS-SVD), but multimodal datasets often have mi…
Large Vision Models Can Solve Mental Rotation Problems
Sebastian Ray Mason, Anders Gjølbye, Phillip Chavarria Højbjerg +2
Mental rotation is a key test of spatial reasoning in humans and has been central to understanding how perception supports cognition. Despite the success of modern vision transform…