Loading
Deep transformers form hierarchical representations, but their expressivity is not well understood. This analysis uses bounded-depth grammars to study how they capture abstract features. The findings could impact language modeling and beyond.
“arXiv:2606.17522v2 Announce Type: replace-cross Abstract: Deep neural networks are widely believed to derive their expressive power from their ability to form \textbf{hierarchical representations}, capturing progressively more abstract and …”
Read the source →STATUS
ACTIVE
CATEGORY
Models
EVIDENCE
Not yet assessed
ENTITY
Deep Transformers, arXiv, Bounded-Depth Grammars
DECISION
Automated · no editorial override
LAST OBSERVED
Aug 8, 2026