AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Debugging Concept Bottleneck Models through Removal and Retraining

Eric Enouen, sainyam galhotra

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Concept bottleneck models

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
remove expert-marked spurious concepts without retraining (ablation)Post-hoc CBM · Waterbirds (user feedback)worst-group accuracy: 25.8 -> 13.9Hurt
remove expert-marked spurious concepts without retraining (ablation)PIP-Net · Waterbirds (user feedback)worst-group accuracy: 71.9 -> 74.4Improved
naive retraining after removal on the biased dataset (ablation)PIP-Net · Waterbirds (user feedback)worst-group accuracy: 71.9 -> 72.5No clear effect
add CBDebug (reweight and augment) retrainingPIP-Net · Waterbirds (user feedback)worst-group accuracy: 71.9 -> 79.4Improved
add CBDebug retrainingPost-hoc CBM · Waterbirds (user feedback)worst-group accuracy: 25.8 -> 51.9Improved
add CBDebug retrainingPost-hoc CBM · CelebA (automated feedback)worst-group accuracy: 8.7 -> 51.3Improved
add augmentation on top of reweighting (ablation)CBDebug on Post-hoc CBM · Waterbirds (user feedback)worst-group accuracy: 55.6 -> 51.9Hurt
add reweighting on top of augmentation (ablation)CBDebug on PIP-Net · Waterbirds (user feedback)worst-group accuracy: 75.5 -> 79.4Improved
add reweighting on top of augmentation (ablation)CBDebug on Post-hoc CBM · ISIC (automated feedback)AUROC: 18.6 -> 58.0Improved
use reweighting only (no augmentation) (ablation)CBDebug on Post-hoc CBM · MetaShift (automated feedback)worst-group accuracy: 84.5 -> 84.1No clear effect
CBDebug removal replaces spurious concepts with robust onesPost-hoc CBM · Waterbirds concept inspectiontop concepts (qualitative)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy