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.
Concept bottleneck models without predefined concepts
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Empirical tests of VLM-CBMs show VLM supervision differs from expert annotations depending on task and that concept accuracy correlates weakly with quality metrics.
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.
-
If Concept Bottlenecks are the Question, are Foundation Models the Answer?
Empirical tests of VLM-CBMs show VLM supervision differs from expert annotations depending on task and that concept accuracy correlates weakly with quality metrics.