A verification algorithm proves that a trained single-layer transformer is 'overwhelmed' by a chosen prefix, meaning its output is insensitive to any appended string of bounded length.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Provably Overwhelming Transformer Models with Designed Inputs
A verification algorithm proves that a trained single-layer transformer is 'overwhelmed' by a chosen prefix, meaning its output is insensitive to any appended string of bounded length.