A claim that null-space leakage yields provable LLM drift detection is undermined by an inverted eigenvalue inference and a sketched regret proof, with no empirical validation.
Understanding intermediate layers using linear classifier probes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift
A claim that null-space leakage yields provable LLM drift detection is undermined by an inverted eigenvalue inference and a sketched regret proof, with no empirical validation.