Concept Flow Models use hierarchical concept-driven decision trees to mitigate information leakage in concept bottleneck models while matching their predictive performance.
Eliminating information leakage in hard concept bottleneck models with supervised, hierarchical concept learning.arXiv preprint arXiv:2402.05945, 2024
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7representative citing papers
Concept-based models can use controlled 'benign' information leakage to remain accurate and intervenable under real-world concept incompleteness by reframing their training objective.
TRACE is a RANO 2.0-aligned concept bottleneck model for 4-class longitudinal glioblastoma response classification on 3D MRI that reports 0.4769 macro F1 on the LUMIERE dataset via 5-fold patient-wise cross-validation.
Sparse autoencoders provide a basis for sensible concept hierarchies on visual data but are undermined by hard and soft feature absorption.
Introduces synthetic benchmarks for concept bottleneck models that control data modality, concept choice, annotation quality, and completeness to evaluate performance in decision support and automation.
Post-hoc CBMs produce unfaithful concept projections due to covariate shifts and systematic label noise; new metrics are introduced to measure faithfulness separately from accuracy.
Formal concept lattices guide staged, hierarchical concept learning in deep networks to produce more interpretable and semantically structured representations.
citing papers explorer
-
Concept Flow Models: Anchoring Concept-Based Reasoning with Hierarchical Bottlenecks
Concept Flow Models use hierarchical concept-driven decision trees to mitigate information leakage in concept bottleneck models while matching their predictive performance.
-
In Defense of Information Leakage in Concept-based Models
Concept-based models can use controlled 'benign' information leakage to remain accurate and intervenable under real-world concept incompleteness by reframing their training objective.
-
Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?
Sparse autoencoders provide a basis for sensible concept hierarchies on visual data but are undermined by hard and soft feature absorption.
-
Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models
Introduces synthetic benchmarks for concept bottleneck models that control data modality, concept choice, annotation quality, and completeness to evaluate performance in decision support and automation.