LLM memorization is concentrated in low-redundancy (high-entropy) samples, which are roughly twice as fragile under prefix perturbation as high-redundancy samples, according to the paper's measurements on Pythia models.
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
-
Beyond Frequency: The Role of Redundancy in Large Language Model Memorization
LLM memorization is concentrated in low-redundancy (high-entropy) samples, which are roughly twice as fragile under prefix perturbation as high-redundancy samples, according to the paper's measurements on Pythia models.