3 citations · 8 across the 9 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Beyond Red-Teaming: Formal Guarantees of LLM Guardrail Classifiers
Nikita Kezins, Urbas Ekka, Pascal Berrang +1
Guardrail Classifiers defend production language models against harmful behavior, but although results seem promising in testing, they provide no formal guarantees. Providing forma…
cs.LG2026
Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
Yatin Dandi, Matteo Vilucchio, Luca Arnaboldi +2
Understanding how deep neural networks learn useful internal representations from data remains a central open problem in the theory of deep learning. We introduce Neural Low-Degree…