In Dyck-language transformers, attention patterns causally use top-of-stack information while residual-stream depth and distance signals are decodable yet causally inert.
URL https://acla nthology.org/2021.acl-long.292/
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dissociating Decodability and Causal Use in Bracket-Sequence Transformers
In Dyck-language transformers, attention patterns causally use top-of-stack information while residual-stream depth and distance signals are decodable yet causally inert.