Large language models display three universal scale-dependent regimes of behavior—stable, chaotic, and signal-dominated—driven by floating-point rounding errors that produce an avalanche effect in early layers.
Ex- ploiting chaotic dynamics as deep neural networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Numerical Instability and Chaos: Quantifying the Unpredictability of Large Language Models
Large language models display three universal scale-dependent regimes of behavior—stable, chaotic, and signal-dominated—driven by floating-point rounding errors that produce an avalanche effect in early layers.