AI RESEARCH

CLIF: Concept-Level Influence Functions for Transparent Bottleneck Models

arXiv CS.CL

ArXi:2605.19848v1 Announce Type: new 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 datasets show that influence functions effectively identify the most impactful