CB-SLICE: Concept-Based Interpretable Error Slice Discovery

• URL: http://arxiv.org/abs/2605.29836v1
• Date: Thu, 28 May 2026 12:16:41 GMT
• Title: CB-SLICE: Concept-Based Interpretable Error Slice Discovery
• Abstract summary: deep learning models often exhibit systematic errors on specific population groups, known as error slices.<n>We introduce CB-SLICE, a concept-based error Slice Discovery Methods (SDM) that groups samples with shared concept prediction failures and identifies the keyword concepts most responsible for each slice's failure mode.<n>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.
• Score: 22.082043372942138
• License: http://creativecommons.org/licenses/by/4.0/
• 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 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.

Related papers

• Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models [105.53190946111586]
  We term this phenomenon object-dependent concept brittleness.<n>We present an interpretability-oriented framework to audit and minimally correct these failures.<n>We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones.
  arXiv  Detail & Related papers  (2026-09-09T09:07:40Z)
• Probabilistic Concept Graph Reasoning for Multimodal Misinformation Detection [50.08054676999716]
  We present Probabilistic Concept Graph Reasoning (PCGR), an interpretable and evolvable framework that reframes multimodal misinformation detection as structured and concept-based reasoning.<n>PCGR achieves state-of-the-art MMD accuracy and robustness to emerging manipulation types, outperforming prior methods in both coarse detection and fine-grained manipulation recognition.
  arXiv  Detail & Related papers  (2026-03-26T09:08:31Z)
• Rethinking Concept Bottleneck Models: From Pitfalls to Solutions [53.84388497227224]
  Concept Bottleneck Models (CBMs) ground predictions in human-understandable concepts.<n>CBM-Suite is a methodological framework to address these challenges.
  arXiv  Detail & Related papers  (2026-03-05T19:37:49Z)
• Debugging Concept Bottleneck Models through Removal and Retraining [11.162969587770094]
  Concept Bottleneck Models (CBMs) use a set of human-interpretable concepts to predict the final task label.<n>These interventions fail to address systemic misalignment between the CBM and the expert's reasoning.<n>We present a general interpretable framework for CBMs that follows a two-step process of Removal and Retraining.
  arXiv  Detail & Related papers  (2025-09-23T18:32:46Z)
• MulCPred: Learning Multi-modal Concepts for Explainable Pedestrian Action Prediction [57.483718822429346]
  MulCPred is proposed that explains its predictions based on multi-modal concepts represented by training samples. MulCPred is evaluated on multiple datasets and tasks.
  arXiv  Detail & Related papers  (2024-09-14T14:15:28Z)
• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)
• Sparse Linear Concept Discovery Models [11.138948381367133]
  Concept Bottleneck Models (CBMs) constitute a popular approach where hidden layers are tied to human understandable concepts. We propose a simple yet highly intuitive interpretable framework based on Contrastive Language Image models and a single sparse linear layer. We experimentally show, our framework not only outperforms recent CBM approaches accuracy-wise, but it also yields high per example concept sparsity.
  arXiv  Detail & Related papers  (2023-08-21T15:16:19Z)
• Explanation Method for Anomaly Detection on Mixed Numerical and Categorical Spaces [0.9543943371833464]
  We present EADMNC (Explainable Anomaly Detection on Mixed Numerical and Categorical spaces) It adds explainability to the predictions obtained with the original model. We report experimental results on extensive real-world data, particularly in the domain of network intrusion detection.
  arXiv  Detail & Related papers  (2022-09-09T08:20:13Z)
• Interpretable Data-Based Explanations for Fairness Debugging [7.266116143672294]
  Gopher is a system that produces compact, interpretable, and causal explanations for bias or unexpected model behavior. We introduce the concept of causal responsibility that quantifies the extent to which intervening on training data by removing or updating subsets of it can resolve the bias. Building on this concept, we develop an efficient approach for generating the top-k patterns that explain model bias.
  arXiv  Detail & Related papers  (2021-12-17T20:10:00Z)
• Meaningfully Explaining a Model's Mistakes [16.521189362225996]
  We propose a systematic approach, conceptual explanation scores (CES) CES explains why a classifier makes a mistake on a particular test sample(s) in terms of human-understandable concepts. We also train new models with intentional and known spurious correlations, which CES successfully identifies from a single misclassified test sample.
  arXiv  Detail & Related papers  (2021-06-24T01:49:55Z)
• Predicting Unreliable Predictions by Shattering a Neural Network [145.3823991041987]
  Piecewise linear neural networks can be split into subfunctions. Subfunctions have their own activation pattern, domain, and empirical error. Empirical error for the full network can be written as an expectation over subfunctions.
  arXiv  Detail & Related papers  (2021-06-15T18:34:41Z)
• Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations [64.85696493596821]
  In computer vision applications, generative counterfactual methods indicate how to perturb a model's input to change its prediction. We propose a counterfactual method that learns a perturbation in a disentangled latent space that is constrained using a diversity-enforcing loss. Our model improves the success rate of producing high-quality valuable explanations when compared to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-03-18T12:57:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.