Linearly Interpretable Concept Embedding Model for Text Classification

Francesco De Santis, Philippe Bich, Gabriele Ciravegna, Pietro Barbiero, Danilo Giordano, Tania Cerquitelli

Keywords: CBM, XAI, Interpretable AI

Abstract:

Despite their success, Large-Language Models (LLMs) still face criticism due to their lack of interpretability.
Traditional post-hoc interpretation methods, based on attention and gradient-based analysis, offer limited insight as they only approximate the model's decision-making processes and have been proved to be unreliable.
For this reason, Concept-Bottleneck Models (CBMs) have been lately proposed in the textual field to provide interpretable predictions based on human-understandable concepts.
However, CBMs still face several criticisms for their architectural constraints limiting their expressivity, for the absence of task-interpretability when employing non-linear task predictors and for requiring extensive annotations that are impractical for real-world text data. In this paper we address these challenges by proposing a novel Linearly Interpretable Concept Embedding Model (LICEM) going beyond the current accuracy-interpretability trade-off. LICEM classification accuracy is better than existing interpretable models and matches black-box models. The provided explanations are more plausible and useful with respect to existing solutions, as attested in a user study. Finally, we show our model can be trained without requiring any concept supervision, as concepts can be automatically predicted by the same LLM backbone.

Primary Area: interpretability and explainable AI

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 6702