A cosine-similarity metric on SHAP feature attributions is proposed to quantify explanation stability for same-label inputs under perturbations in transformer-based sentiment classifiers.
Advances in neural information processing systems34, 18395–18407 (2021)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Empirical Characterization of Rationale Stability Under Controlled Perturbations for Explainable Pattern Recognition
A cosine-similarity metric on SHAP feature attributions is proposed to quantify explanation stability for same-label inputs under perturbations in transformer-based sentiment classifiers.