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.
[Yuksekgonulet al., 2023 ] Mert Yuksekgonul, Maggie Wang, and James Zou
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
SynCB adds a dynamic routing module and joint training to a hybrid concept-plus-neural architecture, reporting up to 3.9 pp higher accuracy than a full neural baseline and up to 6.43 pp better intervention responsiveness than prior hybrids across five datasets.
citing papers explorer
-
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.
-
SynCB: A Synergy Concept-Based Model with Dynamic Routing Between Concepts and Complementary Neural Branches
SynCB adds a dynamic routing module and joint training to a hybrid concept-plus-neural architecture, reporting up to 3.9 pp higher accuracy than a full neural baseline and up to 6.43 pp better intervention responsiveness than prior hybrids across five datasets.