CB-SLICE: Concept-Based Interpretable Error Slice Discovery 事件

CB-SLICE: Concept-Based Interpretable Error Slice Discovery arXiv:2605.29836v1 Announce Type: cross Abstract: 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 inferenc