Delta-Attribution subtracts two models' feature-attribution vectors to audit what changed in a model update, evaluated across 45 settings with a new quality suite.
Fooling LIME and SHAP: Adversarial attacks on post hoc explanation methods,
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
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Delta-Audit: Explaining What Changes When Models Change
Delta-Attribution subtracts two models' feature-attribution vectors to audit what changed in a model update, evaluated across 45 settings with a new quality suite.