AI Paper Atlas

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

Meaningfully debugging model mistakes using conceptual counterfactual explanations

Abubakar Abid, Mert Yuksekgonul, James Zou

ICML 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Post-hoc explanation analysis · 9 citations (OpenAlex)

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
Use joint multiconcept optimization rather than univariate concept scoring (ablation)CCE · MetaDataset, 20 spurious-correlation scenariosPrecision@3: 0.91 -> 0.95Improved
Use joint multiconcept optimization rather than univariate concept scoring (ablation)CCE · MetaDataset, 20 spurious-correlation scenariosMedian rank: 2.00 -> 1.85Improved
Add validity constraints that prevent adding concepts already present or removing concepts already absent (ablation)CCE · Controlled dog-concept and two-confounder examplesPlausibility of explanationsImproved
Use a control model without the induced spurious correlationCCE · MetaDataset, 20 spurious-correlation scenariosPrecision@3: 0.95 -> 0.04Hurt
Use CCE rather than CoCoXSpurious-correlation identification · MetaDataset, 20 spurious-correlation scenariosPrecision@3: 0.73 -> 0.95Improved
Use CCE rather than CSSSpurious-correlation identification · MetaDataset, 20 spurious-correlation scenariosPrecision@3: 0.003 -> 0.95Improved
Use CCE rather than random concept selectionSpurious-correlation identification · MetaDataset, 20 spurious-correlation scenariosPrecision@3: 0.02 -> 0.95Improved
Use a concept library containing the target spurious concept (ablation)CCE · MetaDataset, target concept omitted from the concept bankIdentification of the target conceptMixed
Include the Lateral View concept in the concept libraryCCE · SHC pneumothorax, lateral-view mistakesIdentification of Lateral View as largest negative-score concept: 150/150Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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