Textual Concept Bottleneck Models (TCBMs) are interpretable-by-design models for text classification that predict a set of salient concepts before making the final prediction. This paper proposes Complete Textual Concept Bottleneck Model (CT-CBM), a novel TCBM generator building concept labels in a fully unsupervised manner using a small language model, eliminating both the need for predefined human labeled concepts and LLM annotations. CT-CBM iteratively targets and adds important and identifiable concepts in the bottleneck layer to create a complete concept basis. CT-CBM achieves striking results against competitors in terms of concept basis completeness and concept detection accuracy, offering a promising solution to reliably enhance interpretability of NLP classifiers.
@article{arxiv.2502.11100,
title = {Towards Achieving Concept Completeness for Textual Concept Bottleneck Models},
author = {Milan Bhan and Yann Choho and Pierre Moreau and Jean-Noel Vittaut and Nicolas Chesneau and Marie-Jeanne Lesot},
journal= {arXiv preprint arXiv:2502.11100},
year = {2025}
}