Concept-Based Explanation papers, 2023–2026

Key findings

• Concept-Based Explanation went from 91 papers in 2023 to 117 in 2026, roughly 1.3x in three years.
• NeurIPS publishes the most Concept-Based Explanation work: 134 papers from 2023 to 2026, 39% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 4 in 2023 to 23 in 2026.
• Among the 5 topics under Interpretability, it ranks #3 by 2026 paper count; the fastest grower in the group, Mechanistic Interpretability, is up 8.1x versus 1.3x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026CENDRe: Concept Extraction with Natural Domain Representations
• ICML 2026Evidential Copula Concept Embedding Models
• ICLR 2026Decoupling the Class Label and the Target Concept in Machine Unlearning
• CVPR 2026Agile Deliberation Concept Deliberation for Subjective Visual Classification
• NeurIPS 2025An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations
• ICML 2025Concept-Centric Token Interpretation for Vector-Quantized Generative Models
• ICLR 2025Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning
• CVPR 2025Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models
• NeurIPS 2024[Re] On the Reproducibility of Post-Hoc Concept Bottleneck Models
• ICML 2024ContPhy: Continuum Physical Concept Learning and Reasoning from Videos
• ICLR 2024AttEXplore: Attribution for Explanation with model parameters eXploration
• CVPR 2024Fine-Grained Bipartite Concept Factorization for Clustering
• NeurIPS 2023[Re] Hierarchical Shrinkage: Improving the Accuracy and Interpretability of Tree-Based Methods
• ICML 2023A Closer Look at the Intervention Procedure of Concept Bottleneck Models
• ICLR 2023Concept Gradient: Concept-based Interpretation Without Linear Assumption
• CVPR 2023CRAFT: Concept Recursive Activation FacTorization for Explainability
• NeurIPS 2026Concept frustration: Aligning human concepts and machine representations
• ICML 2026On the Variability of Concept Activation Vectors
• ICLR 2026Hierarchical Concept-based Interpretable Models
• CVPR 2026DCoAR Deep Concept Injection into Unified Autoregressive Models for Personalized

All Concept-Based Explanation papers

71 papers, page 2 of 2

51. NeurIPS 2025CG-SSL: Concept-Guided Self-Supervised Learning
52. NeurIPS 2025Collective Counterfactual Explanations: Balancing Individual Goals and Collective Dynamics
53. NeurIPS 2025Concept Incongruence: An Exploration of Time and Death in Role Playing
54. NeurIPS 2025Concept-Guided Interpretability via Neural Chunking
55. NeurIPS 2025Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts
56. NeurIPS 2025Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition
57. NeurIPS 2025Disentangling Superpositions: Interpretable Brain Encoding Model with Sparse Concept Atoms
58. NeurIPS 2025EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment
59. NeurIPS 2025FACE: Faithful Automatic Concept Extraction
60. NeurIPS 2025FaCT: Faithful Concept Traces for Explaining Neural Network Decisions
61. NeurIPS 2025Generalization vs Specialization under Concept Shift
62. NeurIPS 2025Learning to Condition: A Neural Heuristic for Scalable MPE Inference
63. NeurIPS 2025Object-Centric Concept-Bottlenecks
64. NeurIPS 2025Obliviator Reveals the Cost of Nonlinear Guardedness in Concept Erasure
65. NeurIPS 2025Preserving Task-Relevant Information Under Linear Concept Removal
66. NeurIPS 2025Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry
67. NeurIPS 2025RCCDA: Adaptive Model Updates in the Presence of Concept Drift under a Constrained Resource Budget
68. NeurIPS 2025Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens
69. NeurIPS 2025Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
70. NeurIPS 2025When Are Concepts Erased From Diffusion Models?
71. NeurIPS 2025Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation

FAQ

How many Concept-Based Explanation papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

342 in total: 91 in 2023, 63 in 2024, 71 in 2025, 117 in 2026.

How many Concept-Based Explanation papers are at NeurIPS 2026?

NeurIPS 2026 has 40 Concept-Based Explanation papers, versus 25 the year before.

How many Concept-Based Explanation papers are at ICLR 2026?

ICLR 2026 has 24 Concept-Based Explanation papers, versus 19 the year before.

How many Concept-Based Explanation papers are at ICML 2026?

ICML 2026 has 20 Concept-Based Explanation papers, versus 11 the year before.

How many Concept-Based Explanation papers are at CVPR 2026?

CVPR 2026 has 33 Concept-Based Explanation papers, versus 16 the year before.

Which conference publishes the most Concept-Based Explanation papers?

NeurIPS, with 134 papers from 2023 to 2026.