ADFP aligns fingerprint token sampling with student learning dynamics via a proxy model to achieve stronger distillation detection and lower utility loss than prior heuristic methods on GSM8K, OASST1, and MBPP.
Since there are 60 minutes in an hour, 50 minutes is equal to \( \frac{50}{60} = \frac{5}{6} \) hours
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Antidistillation Fingerprinting
ADFP aligns fingerprint token sampling with student learning dynamics via a proxy model to achieve stronger distillation detection and lower utility loss than prior heuristic methods on GSM8K, OASST1, and MBPP.