3 papers
cs.CL2026
Exemplars in Disguise: Pure Exemplar Models Mimic Abstraction-First Learning
Zachary Nicholas Houghton, Vsevolod Kapatsinski
Whether idiosyncratic, item-specific knowledge is learned before abstract class-level generalizations, or vice versa, is a central question in language learning, with exemplar and…
cs.CL2026
The Holistic Storage of Verb+Up Phrases in Text-based and Audio-based Language Models
Zachary Nicholas Houghton, Yu Zhou, Dan Pluth +2
One of the most central aspects of language processing is the ability to trade off between stored representations and abstract knowledge: one must retrieve stored representations,…
cs.CL2026
On the Interpretability of Whisper Encodings Using Sparse Autoencoders
Dan Pluth, Zachary Nicholas Houghton, Yu Zhou +1
While deep transformer-based models have advanced rapidly, their internal mechanisms remain largely a mystery. Recent work has prioritized understanding text-based transformer mode…