mlsanityData to 7 Oct 2026

Prototype-Grounded Concept Models for Verifiable Concept Alignment

arXiv 2604.16076 ↗First posted 17 Apr 2026cs.LG cs.AI cs.NEcited by 1

Not on the map. Why?

Abstract (arXiv)

Concept Bottleneck Models (CBMs) aim to improve interpretability in Deep Learning by structuring predictions through human-understandable concepts, but they provide no way to verify whether learned concepts align with the human's intended meaning, hurting interpretability. We introduce Prototype-Grounded Concept Models (PGCMs), which ground concepts in learned visual prototypes: image parts that serve as explicit evidence for the concepts. This grounding enables direct inspection of concept semantics and supports targeted human intervention at the prototype level to correct misalignments. Empirically, PGCMs achieve similar predictive performance as state-of-the-art CBMs while substantially improving transparency, interpretability, and intervenability.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 29 of its 34 references that are in the map. First posted on arXiv 17 Apr 2026.

Builds on

29 of 34 references.

References · 29

  1. 2023Segment Anythingcited by 8,158
  2. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2020Concept Bottleneck Modelscited by 1,022
  5. 2020Object-Centric Learning with Slot Attentioncited by 865
  6. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  7. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
  8. 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 389
  9. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 388
  10. 2022Post-hoc Concept Bottleneck Modelscited by 289
  11. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  12. 2021Promises and Pitfalls of Black-Box Concept Learning Modelscited by 128
17 more
  1. 2021Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypescited by 120
  2. 2020Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanationscited by 94
  3. 2022Concept Bottleneck Model with Additional Unsupervised Conceptscited by 79
  4. 2022GlanceNets: Interpretabile, Leak-proof Concept-based Modelscited by 73
  5. 2023Interpretable Neural-Symbolic Concept Reasoningcited by 56
  6. 2024Stochastic Concept Bottleneck Modelscited by 49
  7. 2023This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizationscited by 36
  8. 2023A Survey on Knowledge Editing of Neural Networkscited by 34
  9. 2024Causal Concept Graph Models: Beyond Causal Opacity in Deep Learningcited by 28
  10. 2024On the Concept Trustworthiness in Concept Bottleneck Modelscited by 22
  11. 2024Interpretable Concept-Based Memory Reasoningcited by 17
  12. 2024DCBM: Data-Efficient Visual Concept Bottleneck Modelscited by 16
  13. 2025Object Centric Concept Bottleneckscited by 10
  14. 2025Locality-aware Concept Bottleneck Modelcited by 4
  15. 2025Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Modelscited by 3
  16. 2025Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AIcited by 3
  17. 2025Neurosymbolic Object-Centric Learning with Distant Supervisioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Graphical Design of Interpretable Architecturescited by 0