Initialization scale controls whether a transformer learns compositional reasoning or memorized mappings, because reasoning tokens acquire more differentiated embeddings early in training.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
An Analysis for Reasoning Bias of Language Models with Small Initialization
Initialization scale controls whether a transformer learns compositional reasoning or memorized mappings, because reasoning tokens acquire more differentiated embeddings early in training.