Human uncertainty in concept-based ai systems

KM Collins, M Barker, M Espinosa Zarlenga… - Proceedings of the …, 2023 - dl.acm.org
Placing a human in the loop may help abate the risks of deploying AI systems in safety-
critical settings (eg, a clinician working with a medical AI system). However, mitigating risks …

Faithful vision-language interpretation via concept bottleneck models

S Lai, L Hu, J Wang, L Berti-Equille… - The Twelfth International …, 2023 - openreview.net
The demand for transparency in healthcare and finance has led to interpretable machine
learning (IML) models, notably the concept bottleneck models (CBMs), valued for their …

Robust and interpretable medical image classifiers via concept bottleneck models

A Yan, Y Wang, Y Zhong, Z He, P Karypis… - arxiv preprint arxiv …, 2023 - arxiv.org
Medical image classification is a critical problem for healthcare, with the potential to alleviate
the workload of doctors and facilitate diagnoses of patients. However, two challenges arise …

Learning to receive help: Intervention-aware concept embedding models

M Espinosa Zarlenga, K Collins… - Advances in …, 2023 - proceedings.neurips.cc
Abstract Concept Bottleneck Models (CBMs) tackle the opacity of neural architectures by
constructing and explaining their predictions using a set of high-level concepts. A special …

A closer look at the intervention procedure of concept bottleneck models

S Shin, Y Jo, S Ahn, N Lee - International Conference on …, 2023 - proceedings.mlr.press
Abstract Concept bottleneck models (CBMs) are a class of interpretable neural network
models that predict the target response of a given input based on its high-level concepts …

Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning

F Mumuni, A Mumuni - Cognitive Systems Research, 2024 - Elsevier
We review current and emerging knowledge-informed and brain-inspired cognitive systems
for realizing adversarial defenses, eXplainable Artificial Intelligence (XAI), and zero-shot or …

Editable concept bottleneck models

L Hu, C Ren, Z Hu, H Lin, CL Wang, H **ong… - arxiv preprint arxiv …, 2024 - arxiv.org
Concept Bottleneck Models (CBMs) have garnered much attention for their ability to
elucidate the prediction process through a human-understandable concept layer. However …