HypCBM reformulates concept activations as geometric containment in hyperbolic space to produce sparse, hierarchy-aware signals that match Euclidean models trained on 20 times more data.
Post-hoc concept bottleneck models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hyperbolic Concept Bottleneck Models
HypCBM reformulates concept activations as geometric containment in hyperbolic space to produce sparse, hierarchy-aware signals that match Euclidean models trained on 20 times more data.