Menu

Convergent Evolution: How Different Language Models Learn Similar Number Representations
📰
0

Convergent Evolution: How Different Language Models Learn Similar Number Representations

arXiv.org·[Submitted on 22 Apr 2026]·about 1 month ago
#h8UZtsLj
Reading 0:00
15s threshold

View PDF HTML (experimental) Abstract: Language models trained on natural text learn to represent numbers using periodic features with dominant periods at $T=2, 5, 10$. In this paper, we identify a two-tiered hierarchy of these features: while Transformers, Linear RNNs, LSTMs, and classical word embeddings trained in different ways all learn features that have period-$T$ spikes in the Fourier domain, only some learn geometrically separable features that can be used to linearly classify a number mod-$T$. To explain this incongruity, we prove that Fourier domain sparsity is necessary but not sufficient for mod-$T$ geometric separability. Empirically, we investigate when model training yields geometrically separable features, finding that the data, architecture, optimizer, and tokenizer all play key roles.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.

Read More