A causal audit via neuron-row zeroing shows attribution methods (LRP, IG) faithfully identify dispensable neurons and can install refusal behavior, while rank-stability proxies systematically miss selector failures.
IEEE Transactions 16 G
3 Pith papers cite this work, alongside 1,163 external citations. Polarity classification is still indexing.
3
Pith papers citing it
1,163
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
LRP on EEG transformers reveals Clever Hans artifacts in motor imagery tasks and a recurring central electrode cluster as a candidate sensorimotor signature of arousal.
Synthetic experiments reveal that class-dependent effects appear in both perturbation-based and ground-truth evaluations of time series feature attributions, often producing contradictory rankings of attribution quality due to differences in feature amplitude or temporal extent between classes.
citing papers explorer
-
Faithfulness to Refusal: A Causal Audit of Neuron Selectors
A causal audit via neuron-row zeroing shows attribution methods (LRP, IG) faithfully identify dispensable neurons and can install refusal behavior, while rank-stability proxies systematically miss selector failures.
-
From Clever Hans to Scientific Discovery: Interpreting EEG Foundational Transformers with LRP
LRP on EEG transformers reveals Clever Hans artifacts in motor imagery tasks and a recurring central electrode cluster as a candidate sensorimotor signature of arousal.
-
Why Do Class-Dependent Evaluation Effects Occur with Time Series Feature Attributions? A Synthetic Data Investigation
Synthetic experiments reveal that class-dependent effects appear in both perturbation-based and ground-truth evaluations of time series feature attributions, often producing contradictory rankings of attribution quality due to differences in feature amplitude or temporal extent between classes.