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
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
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
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: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
arXiv:2606. 00202v1 Announce Type: cross Abstract: Standard machine learning pipelines often admit many near-optimal models.
By Zakk Heile, Hayden McTavish, Varun Babbar, Margo Seltzer, Cynthia Rudin
arXiv:2601. 07965v2 Announce Type: replace Abstract: When a model knows when it does not know, many possibilities emerge.
By Chenjie Hao, Weyl Lu, Yuko Ishiwaka, Zengyi Li, Weier Wan, Yubei Chen
arXiv:2606. 00082v1 Announce Type: cross Abstract: Explainability of deep learning algorithms is critical for computer-vision applications with high-stake decisions.
By Cl\'ement B\'enard, Manon Arfib, Christophe Labreuche, Victor Qu\'etu
arXiv:2609.38603v1 Announce Type: new
Abstract: While earth observation models have advanced substantially, they still lack interpretability. While concept-bottleneck models provide interpretability...
By Rishabh Mondal, Nipun Batra, Utkarsh Mall
arXiv:2506. 14126v2 Announce Type: replace-cross Abstract: Modern deep learning is increasingly characterized by the use of open-weight foundation models that can be fine-tuned on specialized datasets.
By Stefan Horoi, Guy Wolf, Eugene Belilovsky, Gintare Karolina Dziugaite
arXiv:2606. 13934v1 Announce Type: new Abstract: Humans cannot always intuit what scenarios are most challenging to LLMs.
By Jennifer Meng Lu, Ruochen Zhang, Isabelle Lee, David Alvarez-Melis, Ellie Pavlick, Naomi Saphra
arXiv:2606. 19882v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) enhance the interpretability of deep learning networks by aligning the features extracted from images with natural concepts.
By Tongqing Shi, Ge Yan, Tuomas Oikarinen, Tsui-Wei Weng