Set-level data entropy estimators show linear correlation with LLM memorization scores, forming the Entropy-Memorization Linearity.
LLM dataset inference: Did you train on my dataset? InThe Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Data Compressibility Quantifies LLM Memorization
Set-level data entropy estimators show linear correlation with LLM memorization scores, forming the Entropy-Memorization Linearity.