α-TCAV replaces TCAV's hard indicator with a tunable smooth function to create a unified probabilistic framework with lower variance and guidance for parameter choice or Bayes-optimal scoring.
arXiv preprint arXiv:2404.03713 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
E-TCAV shows that penultimate-layer proxies yield TCAV scores agreeing with earlier layers while delivering linear speedups in computation.
citing papers explorer
-
$\alpha$-TCAV: A Unified Framework for Testing with Concept Activation Vectors
α-TCAV replaces TCAV's hard indicator with a tunable smooth function to create a unified probabilistic framework with lower variance and guidance for parameter choice or Bayes-optimal scoring.
-
E-TCAV: Formalizing Penultimate Proxies for Efficient Concept Based Interpretability
E-TCAV shows that penultimate-layer proxies yield TCAV scores agreeing with earlier layers while delivering linear speedups in computation.