概念解释论文趋势 2023–2026

主要结论

• 概念解释论文从 2023 年的 91 篇增长到 2026 年的 117 篇，三年间扩大到约 1.3 倍。
• NeurIPS 是发概念解释论文最多的会议，2023–2026 年共 134 篇，占四个会议总量的 39%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 4 篇增至 2026 年的 23 篇。
• 在「可解释性」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的机制解释是 8.1 倍，概念解释是 1.3 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部概念解释论文

共 117 篇，第 3 / 3 页

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

常见问题

2023–2026 年四大会议一共有多少篇概念解释论文？

共 342 篇，按年份分别是 2023 年 91 篇、2024 年 63 篇、2025 年 71 篇、2026 年 117 篇。

NeurIPS 2026 有多少篇概念解释论文？

NeurIPS 2026 有 40 篇概念解释论文，上一届是 25 篇。

ICLR 2026 有多少篇概念解释论文？

ICLR 2026 有 24 篇概念解释论文，上一届是 19 篇。

ICML 2026 有多少篇概念解释论文？

ICML 2026 有 20 篇概念解释论文，上一届是 11 篇。

CVPR 2026 有多少篇概念解释论文？

CVPR 2026 有 33 篇概念解释论文，上一届是 16 篇。

哪个会议的概念解释论文最多？

NeurIPS，2023–2026 年共 134 篇。