SoKA combines Kronecker-product SVD initialization with spectrum-based rank selection, using 25% fewer parameters than PiSSA on LLaMA2-7B while trailing PiSSA by less than one point on three benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Singular Value Decomposition on Kronecker Adaptation for Large Language Model
SoKA combines Kronecker-product SVD initialization with spectrum-based rank selection, using 25% fewer parameters than PiSSA on LLaMA2-7B while trailing PiSSA by less than one point on three benchmarks.