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

117 papers, page 3 of 3

101. NeurIPS 2026NeuroFaith: Evaluating Mechanistic Faithfulness of LLM Free Text Self-Explanation at the Concept Level
102. NeurIPS 2026NORMA: Norm-Guided Explanation Subgraph Discovery
103. NeurIPS 2026On the Provable Emergence of Hierarchical Concept Structure in CLIP Embeddings
104. NeurIPS 2026PLACE: Patch-Level Agnostic Concept Extraction
105. NeurIPS 2026Position Without Positional Embeddings: A Directional Mechanism in NoPE Transformers
106. NeurIPS 2026Position-aware eXplanation: A Model-Agnostic Framework for Positional Attributions
107. NeurIPS 2026Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants
108. NeurIPS 2026Predictive Surprise as Self-Grounding Concept Bottleneck for Interpretable Time Series
109. NeurIPS 2026Second-Order Complexity Theory for Risk, Explanation, and Calibration in Machine Learning
110. NeurIPS 2026Settling the Sample Complexity of Deterministic Agnostic PAC Learning
111. NeurIPS 2026Simultaneous Gradient Learning in First-Price Auctions
112. NeurIPS 2026TanGCE: Manifold-Aware Concept Erasure
113. NeurIPS 2026The Quiet Prompt: Erasing Ineffable Styles from Diffusion Models via Concept Leakage-aware Negative Guidance
114. NeurIPS 2026The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail
115. NeurIPS 2026TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation
116. NeurIPS 2026Weakly Supervised Concept Learning for Interpreting and Attributing LVLM Predictions
117. NeurIPS 2026You Can’t Have It Both Ways: Concept Entanglement Limits Diffusion Model Unlearning

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.