The Counting Power of Transformers
Marco Sälzer, Chris Köcher, Alexander Kozachinskiy, Georg Zetzsche, Anthony W. Lin
Published in ICLR, 2026
We study how transformers reason about the number of occurrences of tokens. We show that they can express counting conditions involving polynomial inequalities, and identify a class of softmax transformers that captures exactly these conditions. The resulting connection to Hilbert’s tenth problem also shows that verification is undecidable even for a simple model without positional encodings or masking.
An earlier preprint was titled NoPE: The Counting Power of Transformers with No Positional Encodings.
