Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

CB-SLICE: Concept-Based Interpretable Error Slice Discovery

About

Despite strong average-case performance, deep learning models often exhibit systematic errors on specific population groups, known as error slices. Identifying these groups and the root causes of their failures is critical for model debugging and bias mitigation. However, existing error Slice Discovery Methods (SDMs) typically generate explanations disconnected from the model's inference process, thus only approximating the underlying error source and may be inaccurate. We address this limitation by leveraging Concept Bottleneck Models (CBMs), whose predictions are directly dependent on human-understandable semantic concepts. Since downstream task failures in CBMs commonly arise from concept mispredictions, concept representations provide a strong candidate for error slice identification, offering fine-grained explanations directly linked to the error source. Building on this insight, we introduce CB-SLICE, a concept-based SDM that groups samples with shared concept prediction failures and identifies the keyword concepts most responsible for each slice's failure mode. Across multiple benchmarks, we show that CB-SLICE outperforms state-of-the-art methods in uncovering well-known biases while providing richer and more faithful explanations of model errors.

Yael Konforti, Mateo Espinosa Zarlenga, Elaf Almahmoud, Mateja Jamnik• 2026

Related benchmarks

TaskDatasetResultRank
Error slice discoveryWaterbirds
Precision@1083
17
Error slice discoveryCelebA
Precision@1092
17
Error slice discoveryMetaShift
Precision@1091
17
Error slice discoveryMNIST-Sum
Precision@10100
17
Showing 4 of 4 rows

Other info

Follow for update