Transformers are limited to a linearly growing number of accessible output sequences with prompt length, with exponential decay in accessible proportion beyond a critical point, even under unbounded context.
Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers , url =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
How Many Different Outputs Can a Transformer Generate?
Transformers are limited to a linearly growing number of accessible output sequences with prompt length, with exponential decay in accessible proportion beyond a critical point, even under unbounded context.