Towards Achieving Concept Completeness for Textual Concept Bottleneck Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916763721007104 |
|---|---|
| author | Bhan, Milan Choho, Yann Moreau, Pierre Vittaut, Jean-Noel Chesneau, Nicolas Lesot, Marie-Jeanne |
| author_facet | Bhan, Milan Choho, Yann Moreau, Pierre Vittaut, Jean-Noel Chesneau, Nicolas Lesot, Marie-Jeanne |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_11100 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Achieving Concept Completeness for Textual Concept Bottleneck Models Bhan, Milan Choho, Yann Moreau, Pierre Vittaut, Jean-Noel Chesneau, Nicolas Lesot, Marie-Jeanne Computation and Language 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. |
| title | Towards Achieving Concept Completeness for Textual Concept Bottleneck Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.11100 |