Latent Concept-based Explanation of NLP Models

arXiv:2404.12545v1 Announce Type: new
Abstract: Interpreting and understanding the predictions made by deep learning models poses a formidable challenge due to their inherently opaque nature. Many previous efforts aimed at explaining these predictions rely on input features, specifically, the words within NLP models. However, such explanations are often less informative due to the discrete nature of these words and their lack of contextual verbosity. To address this limitation, we introduce the Latent Concept Attribution method (LACOAT), which generates explanations for …

abstract arxiv challenge concept cs.cl deep learning features however nature nlp nlp models predictions type understanding words