Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
When Behavioral Safety Evaluation Fails: A Representation-Level Perspective
Enyi Jiang, Anders Gjølbye, Yibo Jacky Zhang +1
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…
cs.LG2026
Missing-Data-Induced Phase Transitions in Spectral Partial Least Squares
Anders Gjølbye, Ida Kargaard, Emma Kargaard +3
Spectral partial least squares (PLS-SVD) estimates the directions shared by two views of the same samples. We analyze it using a rank-one regression model, with entries of both vie…