Concept-Based Explanations

Overview

Concept-based explanations study how to describe a model’s decisions using meaningful features—such as objects, clinical findings, or sound patterns—instead of only pixels or hidden activations. Approaches include concept bottlenecks and activation vectors, sparse autoencoders and dictionaries, language-grounded concepts, and concept graphs or circuits; they are used in settings from image classification and medical diagnosis to time series and language models. Researchers test explanations with concept insertion, deletion, ablation, counterfactuals, and comparisons with human judgments, while also using concepts to audit shortcuts or steer model behavior. A central challenge is ensuring that concepts are both understandable and faithful: a feature may be easy to identify without actually driving the prediction, and greater transparency can sometimes come with reduced accuracy or incomplete explanations.

Latest papers

CardsList

83 papers8 papers in the last four weeks, down 20% on the four weeks before. 0.1% of all new papers.

  1. Procedure without Judgment: What Small Language Models Learn under an Exact Verifier

    Nov 16, 2026Arunkumar V, Manoranjan Gandhudi, Gangadharan G. R. +2llm agent policy complianceConcept-Based Explanations

  2. Understanding Contextual Bias in Agricultural CNNs Through Hidden-Neuron Concept Induction

    Nov 13, 2026Abhilekha Dalal, Avishek Das, Samatha Ereshi AkkamahadeviConvolutional Neural NetworksNeuron-Level Interpretability

  3. Causal Concept Explanations for Deep Neural Models

    Nov 10, 2026Josh Rountree, Pulkit Verma, Oswin So +2Concept-Based ExplanationsNeural Network Interpretability

  4. A Concept-Based Interpretable Framework for Clinical Text-based Prediction via Token-Concept Attention without Concept Supervision

    Nov 10, 2026Jifan Gao, Junjie Hu, John Caskey +6Concept-Based ExplanationsConcept Bottleneck Models

  5. How a Model's Architecture and Performance Influences Explainability: A Study of Grad-CAM and CRAFT in CNN-Based Image Classification

    Nov 9, 2026Kilian Göller, Haadia Amjad, Steffen Seitz +2Explainable Image ClassificationExplainability Evaluation

  6. TraCE: Trajectory-Aware Concepts for Explainable Video Understanding

    Nov 4, 2026Wooil Lee, Junpyo Hong, Jongseo Lee +3Video UnderstandingConcept-Based Explanations

  7. Domain-specific language alignment of multimodal embeddings towards explainable predictions

    Oct 16, 2026Gabrielė Tijūnaitytė, Thijs L. van der Plas, Mohamed-Bachir Belaid +3Multimodal EmbeddingConcept-Based Explanations

  8. PiCo: Physics-Informed Concept Probing for Geo-Foundation Models

    Oct 14, 2026Yihang She, Andrew Blake, Jianbo Qi +1Geospatial Foundation ModelsConcept-Based Explanations

  9. A Concept-informed Interpretable Artificial Intelligence Framework for Breast Ultrasound Diagnosis

    Oct 12, 2026Shengzhou Zhong, Ziying Wang, Liang Li +14Clinical Decision SupportExplainable Medical Image Analysis

  10. Hide and Seek: HIDE Concepts to SEEK explanations for black box models

    Oct 9, 2026Bhanu Tokas, Rahul Nair, Rockwell Jackson +1Interpretable MLConcept-Based Explanations

  11. Revisiting Explainable AI through Model-Independent Concept Dictionaries

    Oct 7, 2026Thomas Schnake, Doreen Schöppenthau, Alexander Meyer +3Explainable Artificial IntelligenceInterpretable ML

  12. ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution

    Oct 3, 2026Yehonatan Elisha, Oren Barkan, Ziv Weiss Haddad +1Concept Activation VectorsConcept-Based Explanations

  13. A Unifying Framework of Concept-based Explainable AI with Completeness Guarantees

    Sep 28, 2026Vojtěch Kůr, Adam Kukučka, Tomáš Brázdil +1Concept-Based ExplanationsNeural Network Interpretability

  14. Uncovering shortcut learning in audio classifiers by discovering recurring concepts in temporal explanations

    Sep 27, 2026Cecilia Bolaños, Luciana Ferrer, Magdalena FuentesConcept-Based ExplanationsClassification

  15. "World Knowledge" in the Weights: Reading Concept Circuits of Vision Transformers

    Sep 8, 2026Yanlin Chen, Tang Li, Xi PengTransformer InterpretabilityVision Foundation Models

  16. What Does Animal Re-Identification Learn? Linear Biological Concepts and Their Origins in Visual Representations

    Sep 5, 2026Robert Nolting, Alexandra Schild, Moritz Weckbecker +2Animal Re-IdentificationVisual Representation Learning

  17. Latent Cluster Analysis for Vision-Language-Action Models

    Sep 2, 2026Theodor Wulff, Sergio Lanza, Tamara Bila +3Vision-Language-Action ModelsClustering

  18. ICON decomposition: Multivariate concept auditing reveals shortcuts that neural networks rely on

    Aug 26, 2026Roshan Prakash Rane, Marco Simnacher, Manuel Pfeuffer +7Concept-Based ExplanationsNeural Network Interpretability

  19. EXPL-FR: Explaining Face Recognition Models via Vision-Language Alignment

    Aug 21, 2026Guray Ozgur, Mustafa Efe Tamyapar, Naser Damer +1Face RecognitionConcept-Based Explanations

  20. Concept-based explanation of gene expression prediction from H&E images

    Aug 17, 2026Amos Muench, Jonathan Thielmann, Reduan Achtibat +9Gene Expression Prediction from Histopathology ImagesComputational Pathology

  21. Identifying Confusion Trends in Concept-based XAI for Multi-Label Classification

    Aug 16, 2026Haadia Amjad, Ronald TetzlaffDataset BiasConcept-Based Explanations

  22. When Do Concepts Become Functionally Sufficient During Language-Model Training?

    Aug 15, 2026Raphael Bernas, Paul G. Chevalier, Fanny Jourdan +1LLM InterpretabilityTransformer Interpretability

  23. SAGE: Semantic Explainability of Attention-Based Survival Models in Computational Pathology

    Aug 3, 2026Abdallah Lamane, Abdul Rahman Diab, Ren-Chin Wu +1Computational PathologyCancer Survival Prediction

  24. Explaining Image Similarity with Automatically Extracted Concept Activation Vectors

    Jul 30, 2026Isaac Roberts, Petra Bevandic, Alexander Schulz +1Concept-Based ExplanationsConcept Activation Vectors