Contrast-CAT: Contrasting Activations for Enhanced Interpretability in Transformer-based Text Classifiers

Contrast-CAT: Contrasting Activations for Enhanced Interpretability in Transformer-based Text Classifiers
제목
Contrast-CAT: Contrasting Activations for Enhanced Interpretability in Transformer-based Text Classifiers
제목 (타언어)
Contrast-CAT: Contrasting Activations for Enhanced Interpretability in Transformer-based Text Classifiers
저자
Lee, Sangkyun
발행일
2025-07-22
학회명
Conference on Uncertainty in Artificial Intelligence (UAI)
개최국가
브라질
학회 개최일
2025-07-21 ~ 2025-07-25