DEL is a new loss for LLM numerical learning that applies supervised digit entropy optimization and extends to floating-point numbers, showing improved accuracy and distance metrics over prior methods on math benchmarks.
A neural probabilistic language model
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
citing papers explorer
-
DEL: Digit Entropy Loss for Numerical Learning of Large Language Models
DEL is a new loss for LLM numerical learning that applies supervised digit entropy optimization and extends to floating-point numbers, showing improved accuracy and distance metrics over prior methods on math benchmarks.
- Language Model Networks: Supervision-Efficient Learning through Dense Communication