Prototype-Grounded Concept Models for Verifiable Concept Alignment
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations
Learning visual concepts from raw images without strong supervision is a challenging task. In this work, we show the advantages of prototype representations for understanding and revising the latent space of neural conce…
DisentanglementBeyond Patches: Mining Interpretable Part-Prototypes for Explainable AI
Deep learning has provided considerable advancements for multimedia systems, yet the interpretability of deep models remains a challenge. State-of-the-art post-hoc explainability methods, such as GradCAM, provide visual …
Unsupervised Part DiscoveryUsing Grounded Word Representations to Study Theories of Lexical Concepts
The fields of cognitive science and philosophy have proposed many different theories for how humans represent {``}concepts{''}. Multiple such theories are compatible with state-of-the-art NLP methods, and could in princi…
PhilosophyMCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes
Recent advancements in post-hoc and inherently interpretable methods have markedly enhanced the explanations of black box classifier models. These methods operate either through post-analysis or by integrating concept le…
ClassificationDecision MakingExplainable Artificial Intelligence (XAI)AI Integrity: A New Paradigm for Verifiable AI Governance
AI systems increasingly shape high-stakes decisions in healthcare, law, defense, and education, yet existing governance paradigms -- AI Ethics, AI Safety, and AI Alignment -- share a common limitation: they evaluate outc…