CLIF: Concept-Level Influence Functions for Transparent Bottleneck Models 事件

CLIF: Concept-Level Influence Functions for Transparent Bottleneck Models arXiv:2605.19848v2 Announce Type: replace Abstract: In recent years, the black-box nature of deep learning models has limited their application in high-stakes domains such as medical diagnosis and finance, where interpretability is essential. To address this, we propose a novel approach using influence functions to enhance interpretability in NLP models at both the sample and concept levels. Experiments on CEBaB and Yelp