Modern text encoders resist second-order collapse under mean pooling because token embeddings concentrate tightly within texts, and this resistance correlates with stronger downstream performance.
Specifi- cally, the expected cosine similarity between to- ken embeddings within the same text satisfies Ej<k [cos(xi,j,x i,k)]≥1/3
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
-
Why Mean Pooling Works: Quantifying Second-Order Collapse in Text Embeddings
Modern text encoders resist second-order collapse under mean pooling because token embeddings concentrate tightly within texts, and this resistance correlates with stronger downstream performance.