Hyperfitting improves LLM generation via context-dependent rank reordering from geometric expansion in the terminal transformer block, distinct from temperature scaling, and enables efficient Late-Stage LoRA fine-tuning.
URL https://www.sciencedirect.com/sc ience/article/pii/S0167278925003367
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Proposes a two-gradient-field model with candidate order parameters alpha_dagger and kappa_c to unify phase transitions across learning theory and non-equilibrium chemistry.
citing papers explorer
-
Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion
Hyperfitting improves LLM generation via context-dependent rank reordering from geometric expansion in the terminal transformer block, distinct from temperature scaling, and enables efficient Late-Stage LoRA fine-tuning.
-
Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry
Proposes a two-gradient-field model with candidate order parameters alpha_dagger and kappa_c to unify phase transitions across learning theory and non-equilibrium chemistry.