Salvato in:
Dettagli Bibliografici
Autori principali: Bhan, Milan, Choho, Yann, Moreau, Pierre, Vittaut, Jean-Noel, Chesneau, Nicolas, Lesot, Marie-Jeanne
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2502.11100
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
Sommario:
  • 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.