WeightWatcher K-matrix power-law exponent tracks LLM memorization with ρ ≈ -0.90

rickasaurus · x · 2026-09-24

A preliminary analysis applies WeightWatcher to study how LLMs memorize random inputs: when part of the training data is deliberately corrupted with random labels, the model eventually memorizes them and clean test accuracy degrades.

Monitoring weight spectra throughout training reveals a strong, layer-specific signal:

The α exponent could serve as a real-time in-training monitor for memorization.

Original post →

More from Research

Research channel →