The paper introduces CREAMs, a flexible framework for Concept Bottleneck Models that allows explicit encoding of concept‑concept and concept‑task relationships such as mutual exclusivity, hierarchy, and correlations. CREAMs can optionally use a regularized side‑channel to compensate for incomplete concept sets, maintaining competitive performance while encouraging concept‑grounded predictions. The authors also propose a new metric to assess interpretability when predictions partially rely on the side‑channel, and demonstrate that CREAMs support efficient interventions, avoid concept leakage, and match black‑box performance even with missing concepts.
By Nektarios Kalampalikis, Kavya Gupta, Georgi Vitanov, Isabel Valera
The paper investigates how interventions on intermediate concepts in concept‑based models can sometimes worsen downstream predictions, a problem termed intervention harm. It shows that the previously proposed leakage‑mitigation objective, which optimises for full‑concept interventions, does not reliably prevent harm when only a subset of concepts is altered. The authors propose a new monotonic intervention objective that penalises increases in task loss during partial interventions, and demonstrate that combining this with the endpoint objective substantially reduces both the frequency and severity of partial‑intervention harm while maintaining overall model performance.
By Gregory Verghese, Christopher J. Soelistyo, Mateo Espinosa Zarlenga, Alessandro Barp, Christopher R. S. Banerji
arXiv:2606. 04326v1 Announce Type: cross Abstract: Concept bottleneck models predict outcomes from high-level concepts detected in inputs.
By Julian Skirzynski, Harry Cheon, Shreyas Kadekodi, Meredith Stewart, Berk Ustun
Concept bottleneck models predict outcomes from high-level concepts detected in inputs. Although concepts provide a simple way to reap benefits from interpretability, very few datasets include concept labels.
arXiv:2609.38625v1 Announce Type: cross
Abstract: Concept Bottleneck Models (CBMs) are designed to provide interpretable intermediate representations, yet how such bottlenecks affect robustness remai...
By Hanwei Zhang, Tianma Hu, Gaojie Jin, Xu Cheng, Ronghui Mu
arXiv:2608. 10004v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) provide an interpretable framework by grounding predictions in human-understandable concepts, enabling semantic inspection and test-time intervention.
By An Sui, Yuzhu Li, Fuping Wu, Xiahai Zhuang
arXiv:2602. 02886v3 Announce Type: replace-cross Abstract: Concept Bottleneck Models (CBMs) promote interpretability by grounding predictions in human-understandable concepts.
By Francesco De Santis, Gabriele Ciravegna, Giovanni De Felice, Arianna Casanova, Francesco Giannini, Michelangelo Diligenti, Johannes Schneider, Danilo Giordano, Mateo Espinosa Zarlenga, Pietro Barbiero
arXiv:2606. 16535v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) are a relevant tool for explainable Artificial Intelligence because they make their predictions through human-interpretable symbols.
By Javier Fumanal-Idocin, Javier Andreu-Perez
arXiv:2606. 30498v1 Announce Type: cross Abstract: Human decision-making interprets the world through high-level concepts, such as recognizing a bird by its belly color.
By Laines Schmalwasser, Jan Blunk, Niklas Penzel, Julia Niebling, Joachim Denzler
The paper presents a plug‑and‑play framework that uses concept-based interpretation to debug medical imaging models. By aligning a single‑modality encoder with BioMedCLIP, the authors build a Concept Bottleneck Model that allows concept‑level interventions to distinguish causal from spurious features. Experiments on Mayo Clinic ultrasound and CheXpert chest X‑ray data show that these interventions can reliably diagnose model issues and even improve performance through guided fine‑tuning.
By Samrajya Thapa, Daniel J. Quest, Timothy L. Kline, Carrie L. Langstraat, Emanuel C. Trabuco, Wei Le
The paper introduces a method for efficiently exploring the Rashomon set of Concept Bottleneck Models (CBMs) by using a parallel parameter‑efficient adaptation module, checkpointing, and a concept diversity objective. This approach generates multiple equally accurate CBMs from a single training process, achieving greater diversity than baseline methods while consuming less memory. The resulting diverse models enable trustworthy selection, reduce inter‑class confusion, and support reliable abstention in decision‑making.
By Shihan Feng, Cheng Zhang, Michael Xi, Ethan Hsu, Lesia Semenova, Chudi Zhong
CLEAN (Continual Learning with Expandable and Architecturally Isolated Networks) is an incremental cognitive diagnosis framework that allows the concept space to grow while guaranteeing that historical diagnoses remain unchanged. It achieves this by freezing past diagnostic functions, applying orthogonal column masking to prevent gradient interference, and adding expandable full‑rank branches with micro‑variance initialization for new concepts. Experiments on three large‑scale educational datasets show that CLEAN attains zero Representation Drift, preserving old‑item metrics exactly while performing competitively on new items.
By Tao He, Jinxing Xiang, Fan Jiang